Merge branch 'dev'

Co-authored-by: github-actions <41898282+github-actions[bot]@users.noreply.github.com>

.codecov.yml

@@ -1,19 +1,36 @@
+codecov:
+  require_ci_to_pass: true
+# https://docs.codecov.com/docs/flags#recommended-automatic-flag-management
+# Require each flag to have 1 upload before notification
+flag_management:
+  individual_flags:
+    - name: backend
+      paths:
+        - src/
+    - name: frontend
+      paths:
+        - src-ui/
 # https://docs.codecov.com/docs/pull-request-comments
 # codecov will only comment if coverage changes
 comment:
   require_changes: true
+  # https://docs.codecov.com/docs/javascript-bundle-analysis
+  require_bundle_changes: true
+  bundle_change_threshold: "50Kb"
 coverage:
   status:
     project:
       default:
         # https://docs.codecov.com/docs/commit-status#threshold
         threshold: 1%
-        # https://docs.codecov.com/docs/commit-status#only_pulls
-        only_pulls: true
     patch:
       default:
-        # For the changed lines only, target 75% covered, but
-        # allow as low as 50%
-        target: 75%
+        # For the changed lines only, target 100% covered, but
+        # allow as low as 75%
+        target: 100%
         threshold: 25%
-        only_pulls: true
+# https://docs.codecov.com/docs/javascript-bundle-analysis
+bundle_analysis:
+  # Fail if the bundle size increases by more than 1MB
+  warning_threshold: "1MB"
+  status: true

.codespellrc

@@ -0,0 +1,3 @@
+[codespell]
+write-changes = True
+ignore-words-list = criterias,afterall,valeu,ureue,equest,ure,assertIn

.devcontainer/Dockerfile

@@ -0,0 +1,180 @@
+# syntax=docker/dockerfile:1
+
+FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-slim as main-app
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Buildx provided, must be defined to use though
+ARG TARGETARCH
+
+# Can be workflow provided, defaults set for manual building
+ARG JBIG2ENC_VERSION=0.29
+ARG QPDF_VERSION=11.9.0
+ARG GS_VERSION=10.03.1
+
+# Set Python environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    # Ignore warning from Whitenoise
+    PYTHONWARNINGS="ignore:::django.http.response:517" \
+    PNGX_CONTAINERIZED=1
+
+#
+# Begin installation and configuration
+# Order the steps below from least often changed to most
+#
+
+# Packages need for running
+ARG RUNTIME_PACKAGES="\
+  # General utils
+  curl \
+  # Docker specific
+  gosu \
+  # Timezones support
+  tzdata \
+  # fonts for text file thumbnail generation
+  fonts-liberation \
+  gettext \
+  ghostscript \
+  gnupg \
+  icc-profiles-free \
+  imagemagick \
+  # PostgreSQL
+  postgresql-client \
+  # MySQL / MariaDB
+  mariadb-client \
+  # OCRmyPDF dependencies
+  tesseract-ocr \
+  tesseract-ocr-eng \
+  tesseract-ocr-deu \
+  tesseract-ocr-fra \
+  tesseract-ocr-ita \
+  tesseract-ocr-spa \
+  unpaper \
+  pngquant \
+  jbig2dec \
+  # lxml
+  libxml2 \
+  libxslt1.1 \
+  # itself
+  qpdf \
+  # Mime type detection
+  file \
+  libmagic1 \
+  media-types \
+  zlib1g \
+  # Barcode splitter
+  libzbar0 \
+  poppler-utils \
+  htop \
+  sudo"
+
+# Install basic runtime packages.
+# These change very infrequently
+RUN set -eux \
+  echo "Installing system packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES}
+
+ARG PYTHON_PACKAGES="\
+  python3 \
+  python3-pip \
+  python3-wheel \
+  pipenv \
+  ca-certificates"
+
+RUN set -eux \
+  echo "Installing python packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet ${PYTHON_PACKAGES}
+
+RUN set -eux \
+  && echo "Installing pre-built updates" \
+    && echo "Installing qpdf ${QPDF_VERSION}" \
+      && curl --fail --silent --show-error --location \
+        --output libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && curl --fail --silent --show-error --location \
+        --output qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+    && echo "Installing Ghostscript ${GS_VERSION}" \
+      && curl --fail --silent --show-error --location \
+          --output libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+      && curl --fail --silent --show-error --location \
+          --output ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+      && curl --fail --silent --show-error --location \
+          --output libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+    && echo "Installing jbig2enc" \
+      && curl --fail --silent --show-error --location \
+        --output jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+      && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb
+
+# setup docker-specific things
+# These change sometimes, but rarely
+WORKDIR /usr/src/paperless/src/docker/
+
+COPY [ \
+  "docker/imagemagick-policy.xml", \
+  "./" \
+]
+
+RUN set -eux \
+  && echo "Configuring ImageMagick" \
+    && mv imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
+
+# Packages needed only for building a few quick Python
+# dependencies
+ARG BUILD_PACKAGES="\
+  build-essential \
+  git \
+  # https://www.psycopg.org/docs/install.html#prerequisites
+  libpq-dev \
+  # https://github.com/PyMySQL/mysqlclient#linux
+  default-libmysqlclient-dev \
+  pkg-config \
+  pre-commit"
+
+# hadolint ignore=DL3042
+RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
+  set -eux \
+  && echo "Installing build system packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet ${BUILD_PACKAGES}
+
+RUN set -eux \
+  && npm update npm -g
+
+# add users, setup scripts
+# Mount the compiled frontend to expected location
+RUN set -eux \
+  && echo "Setting up user/group" \
+    && groupmod --new-name paperless node \
+    && usermod --login paperless --home /usr/src/paperless node \
+    && usermod -s /bin/bash paperless \
+    && echo "paperless ALL=(ALL) NOPASSWD:ALL" >> /etc/sudoers \
+  && echo "Creating volume directories" \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/data \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/media \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/consume \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/export \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/.venv \
+  && echo "Adjusting all permissions" \
+    && chown --from root:root --changes --recursive paperless:paperless /usr/src/paperless
+#  && echo "Collecting static files" \
+#    && gosu paperless python3 manage.py collectstatic --clear --no-input --link \
+#    && gosu paperless python3 manage.py compilemessages
+
+VOLUME ["/usr/src/paperless/paperless-ngx/data", \
+        "/usr/src/paperless/paperless-ngx/media", \
+        "/usr/src/paperless/paperless-ngx/consume", \
+        "/usr/src/paperless/paperless-ngx/export", \
+        "/usr/src/paperless/paperless-ngx/.venv"]

.devcontainer/README.md

@@ -0,0 +1,117 @@
+# Paperless NGX Development Environment
+
+## Overview
+
+Welcome to the Paperless NGX development environment! This setup uses VSCode DevContainers to provide a consistent and seamless development experience.
+
+### What are DevContainers?
+
+DevContainers are a feature in VSCode that allows you to develop within a Docker container. This ensures that your development environment is consistent across different machines and setups. By defining a containerized environment, you can eliminate the "works on my machine" problem.
+
+### Advantages of DevContainers
+
+- **Consistency**: Same environment for all developers.
+- **Isolation**: Separate development environment from your local machine.
+- **Reproducibility**: Easily recreate the environment on any machine.
+- **Pre-configured Tools**: Include all necessary tools and dependencies in the container.
+
+## DevContainer Setup
+
+The DevContainer configuration provides up all the necessary services for Paperless NGX, including:
+
+- Redis
+- Gotenberg
+- Tika
+
+Data is stored using Docker volumes to ensure persistence across container restarts.
+
+## Configuration Files
+
+The setup includes debugging configurations (`launch.json`) and tasks (`tasks.json`) to help you manage and debug various parts of the project:
+
+- **Backend Debugging:**
+  - `manage.py runserver`
+  - `manage.py document-consumer`
+  - `celery`
+- **Maintenance Tasks:**
+  - Create superuser
+  - Run migrations
+  - Recreate virtual environment (`.venv` with pipenv)
+  - Compile frontend assets
+
+## Getting Started
+
+### Step 1: Running the DevContainer
+
+To start the DevContainer:
+
+1. Open VSCode.
+2. Open the project folder.
+3. Open the command palette:
+   - **Windows/Linux**: `Ctrl+Shift+P`
+   - **Mac**: `Cmd+Shift+P`
+4. Type and select `Dev Containers: Rebuild and Reopen in Container`.
+
+VSCode will build and start the DevContainer environment.
+
+### Step 2: Initial Setup
+
+Once the DevContainer is up and running, perform the following steps:
+
+1. **Compile Frontend Assets**:
+
+   - Open the command palette:
+     - **Windows/Linux**: `Ctrl+Shift+P`
+     - **Mac**: `Cmd+Shift+P`
+   - Select `Tasks: Run Task`.
+   - Choose `Frontend Compile`.
+
+2. **Run Database Migrations**:
+
+   - Open the command palette:
+     - **Windows/Linux**: `Ctrl+Shift+P`
+     - **Mac**: `Cmd+Shift+P`
+   - Select `Tasks: Run Task`.
+   - Choose `Migrate Database`.
+
+3. **Create Superuser**:
+   - Open the command palette:
+     - **Windows/Linux**: `Ctrl+Shift+P`
+     - **Mac**: `Cmd+Shift+P`
+   - Select `Tasks: Run Task`.
+   - Choose `Create Superuser`.
+
+### Debugging and Running Services
+
+You can start and debug backend services either as debugging sessions via `launch.json` or as tasks.
+
+#### Using `launch.json`:
+
+1. Press `F5` or go to the **Run and Debug** view in VSCode.
+2. Select the desired configuration:
+   - `Runserver`
+   - `Document Consumer`
+   - `Celery`
+
+#### Using Tasks:
+
+1. Open the command palette:
+   - **Windows/Linux**: `Ctrl+Shift+P`
+   - **Mac**: `Cmd+Shift+P`
+2. Select `Tasks: Run Task`.
+3. Choose the desired task:
+   - `Runserver`
+   - `Document Consumer`
+   - `Celery`
+
+### Additional Maintenance Tasks
+
+Additional tasks are available for common maintenance operations:
+
+- **Recreate .venv**: For setting up the virtual environment using pipenv.
+- **Migrate Database**: To apply database migrations.
+- **Create Superuser**: To create an admin user for the application.
+
+## Let's Get Started!
+
+Follow the steps above to get your development environment up and running. Happy coding!

.devcontainer/devcontainer.json

@@ -0,0 +1,16 @@
+{
+    "name": "Paperless Development",
+    "dockerComposeFile": "docker-compose.devcontainer.sqlite-tika.yml",
+    "service": "paperless-development",
+    "workspaceFolder": "/usr/src/paperless/paperless-ngx",
+    "postCreateCommand": "/bin/bash -c pre-commit install && pipenv install --dev",
+    "customizations": {
+        "vscode": {
+            "extensions": [
+              "mhutchie.git-graph",
+              "ms-python.python"
+            ]
+        }
+    },
+    "remoteUser": "paperless"
+  }

.devcontainer/docker-compose.devcontainer.sqlite-tika.yml

@@ -0,0 +1,84 @@
+# Docker Compose file for developing Paperless NGX in VSCode DevContainers.
+# This file contains everything Paperless NGX needs to run.
+# Paperless supports amd64, arm, and arm64 hardware.
+# All compose files of Paperless configure it in the following way:
+#
+# - Paperless is (re)started on system boot if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# SQLite is used as the database. The SQLite file is stored in the data volume.
+#
+# In addition, this Docker Compose file adds the following optional
+# configurations:
+#
+# - Apache Tika and Gotenberg servers are started with Paperless NGX and Paperless
+#   is configured to use these services. These provide support for consuming
+#   Office documents (Word, Excel, PowerPoint, and their LibreOffice counterparts).
+#
+# This file is intended only to be used through VSCOde devcontainers. See README.md
+# in the folder .devcontainer.
+
+
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  # No ports need to be exposed; the VSCode DevContainer plugin manages them.
+  paperless-development:
+    image: paperless-ngx
+    build:
+      context: ../    # Dockerfile cannot access files from parent directories if context is not set.
+      dockerfile: ./.devcontainer/Dockerfile
+    restart: unless-stopped
+    depends_on:
+      - broker
+      - gotenberg
+      - tika
+    volumes:
+      - ..:/usr/src/paperless/paperless-ngx:delegated
+      - ../.devcontainer/vscode:/usr/src/paperless/paperless-ngx/.vscode:delegated # VSCode config files
+      - pipenv:/usr/src/paperless/paperless-ngx/.venv # Pipenv environment persisted in volume
+      - /usr/src/paperless/paperless-ngx/src/documents/static/frontend # Static frontend files exist only in container
+      - /usr/src/paperless/paperless-ngx/src/.pytest_cache
+      - /usr/src/paperless/paperless-ngx/.ruff_cache
+      - /usr/src/paperless/paperless-ngx/htmlcov
+      - /usr/src/paperless/paperless-ngx/.coverage
+      - data:/usr/src/paperless/paperless-ngx/data
+      - media:/usr/src/paperless/paperless-ngx/media
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+      PAPERLESS_STATICDIR: ./src/documents/static
+      PAPERLESS_DEBUG: true
+
+    # Overrides default command so things don't shut down after the process ends.
+    command: /bin/sh -c "chown -R paperless:paperless /usr/src/paperless/paperless-ngx/src/documents/static/frontend && chown -R paperless:paperless /usr/src/paperless/paperless-ngx/.ruff_cache && while sleep 1000; do :; done"
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.10
+    restart: unless-stopped
+
+    # The Gotenberg Chromium route is used to convert .eml files. We do not
+    # want to allow external content like tracking pixels or even JavaScript.
+    command:
+      - "gotenberg"
+      - "--chromium-disable-javascript=true"
+      - "--chromium-allow-list=file:///tmp/.*"
+
+  tika:
+    image: docker.io/apache/tika:latest
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:
+  redisdata:
+  pipenv:

.devcontainer/vscode/launch.json

@@ -0,0 +1,43 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "manage.py runserver",
+            "type": "python",
+            "request": "launch",
+            "program": "${workspaceFolder}/src/manage.py",
+            "console": "integratedTerminal",
+            "justMyCode": true,
+            "args": ["runserver"],
+            "django": true
+        },
+        {
+            "name": "manage.py document_consumer",
+            "type": "python",
+            "request": "launch",
+            "program": "${workspaceFolder}/src/manage.py",
+            "console": "integratedTerminal",
+            "justMyCode": true,
+            "args": ["document_consumer"],
+            "django": true
+        },
+        {
+            "name": "celery",
+            "type": "python",
+            "cwd": "${workspaceFolder}/src",
+            "request": "launch",
+            "module": "celery",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/src"
+              },
+            "args": [
+                "-A",
+                "paperless",
+                "worker",
+                "-l",
+                "DEBUG"
+            ]
+        }
+    ]
+}

.devcontainer/vscode/settings.json

@@ -0,0 +1,11 @@
+{
+    "python.testing.pytestArgs": [
+        "src"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "files.watcherExclude": {
+        "**/.venv/**": true,
+        "**/pytest_cache/**": true
+    }
+}

.devcontainer/vscode/tasks.json

@@ -0,0 +1,136 @@
+{
+	"version": "2.0.0",
+	"tasks": [
+	{
+		"label": "manage.py document_consumer",
+		"type": "shell",
+		"command": "pipenv run python manage.py document_consumer",
+		"group": "build",
+		"presentation": {
+			"echo": true,
+			"reveal": "always",
+			"focus": false,
+			"panel": "shared",
+			"showReuseMessage": false,
+			"clear": true,
+			"revealProblems": "onProblem"
+		},
+		"options": {
+			"cwd": "${workspaceFolder}/src"
+		}
+
+		},
+		{
+			"label": "manage.py runserver",
+			"type": "shell",
+			"command": "pipenv run python manage.py runserver",
+			"group": "build",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": false,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}/src"
+			}
+
+			},
+	  {
+		"label": "Maintenance: manage.py migrate",
+		"type": "shell",
+		"command": "pipenv run python manage.py migrate",
+		"group": "none",
+		"presentation": {
+			"echo": true,
+			"reveal": "always",
+			"focus": true,
+			"panel": "shared",
+			"showReuseMessage": false,
+			"clear": true,
+			"revealProblems": "onProblem"
+		},
+		"options": {
+			"cwd": "${workspaceFolder}/src"
+		}
+	  },
+	  {
+		"label": "Maintenance: manage.py createsuperuser",
+		"type": "shell",
+		"command": "pipenv run python manage.py createsuperuser",
+		"group": "none",
+		"presentation": {
+			"echo": true,
+			"reveal": "always",
+			"focus": true,
+			"panel": "shared",
+			"showReuseMessage": false,
+			"clear": true,
+			"revealProblems": "onProblem"
+		},
+		"options": {
+			"cwd": "${workspaceFolder}/src"
+		}
+	  },
+	  {
+		"label": "compile frontend",
+		"type": "shell",
+		"command": "npm ci && ./node_modules/.bin/ng build --configuration production",
+		"group": "none",
+		"presentation": {
+			"echo": true,
+			"reveal": "always",
+			"focus": true,
+			"panel": "shared",
+			"showReuseMessage": false,
+			"clear": true,
+			"revealProblems": "onProblem"
+		},
+		"options": {
+			"cwd": "${workspaceFolder}/src-ui"
+		}
+	  },
+	  {
+		"label": "Maintenance: recreate .venv",
+		"type": "shell",
+		"command": "rm -R -v .venv/* || pipenv install --dev",
+		"group": "none",
+		"presentation": {
+			"echo": true,
+			"reveal": "always",
+			"focus": true,
+			"panel": "shared",
+			"showReuseMessage": false,
+			"clear": true,
+			"revealProblems": "onProblem"
+		},
+		"options": {
+			"cwd": "${workspaceFolder}"
+		}
+	  },
+	  {
+		"label": "Celery Worker",
+		"type": "shell",
+		"command": "pipenv run celery --app paperless worker -l DEBUG",
+		"group": {
+		  "kind": "build",
+		  "isDefault": true
+		},
+		"presentation": {
+			"echo": true,
+			"reveal": "always",
+			"focus": true,
+			"panel": "shared",
+			"showReuseMessage": false,
+			"clear": true,
+			"revealProblems": "onProblem"
+		},
+		"options": {
+			"cwd": "${workspaceFolder}/src"
+		}
+	  }
+	]
+  }

.dockerignore

@@ -1,21 +1,28 @@
+# Tool caches
 **/__pycache__
-/src-ui/.vscode
-/src-ui/node_modules
-/src-ui/dist
+**/.ruff_cache/
+**/.mypy_cache/
+# Virtual environment & similar
+.venv/
+./src-ui/node_modules
+./src-ui/dist
+# IDE folders
+.idea/
+.vscode/
+./src-ui/.vscode
+# VCS
 .git
-/export
-/consume
-/media
-/data
-/docs
-.pytest_cache
-/dist
-/scripts
-/resources
+# Test related
+**/.pytest_cache
 **/tests
 **/*.spec.ts
 **/htmlcov
-/src/.pytest_cache
-.idea
-.venv/
-.vscode/
+# Local folders
+./export
+./consume
+./media
+./data
+./docs
+./dist
+./scripts
+./resources

.env

@@ -1,2 +1 @@
 COMPOSE_PROJECT_NAME=paperless
-export PROMPT="(pipenv-projectname)$P$G"

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -6,14 +6,21 @@ body:
   - type: markdown
     attributes:
       value: |
-        Have a question? 👉 [Start a new discussion](https://github.com/paperless-ngx/paperless-ngx/discussions/new) or [ask in chat](https://matrix.to/#/#paperlessngx:matrix.org).
+        ### ⚠️ Please remember: issues are for *bugs*
+        That is, something you believe affects every single user of Paperless-ngx, not just you. If you're not sure, start with one of the other options below.
 
-        Before opening an issue, please double check:
+        Also, note that **Paperless-ngx does not perform OCR or archive file creation itself**, those are handled by other tools. Problems with OCR or archive versions of specific files should likely be raised 'upstream', see https://github.com/ocrmypdf/OCRmyPDF/issues or https://github.com/tesseract-ocr/tesseract/issues
+  - type: markdown
+    attributes:
+      value: |
+        #### Have a question? 👉 [Start a new discussion](https://github.com/paperless-ngx/paperless-ngx/discussions/new) or [ask in chat](https://matrix.to/#/#paperlessngx:matrix.org).
+
+        #### Before opening an issue, please double check:
 
         - [The troubleshooting documentation](https://docs.paperless-ngx.com/troubleshooting/).
         - [The installation instructions](https://docs.paperless-ngx.com/setup/#installation).
         - [Existing issues and discussions](https://github.com/paperless-ngx/paperless-ngx/search?q=&type=issues).
-        - Disable any customer container initialization scripts, if using any
+        - Disable any custom container initialization scripts, if using
 
         If you encounter issues while installing or configuring Paperless-ngx, please post in the ["Support" section of the discussions](https://github.com/paperless-ngx/paperless-ngx/discussions/new?category=support).
   - type: textarea
@@ -79,19 +86,33 @@ body:
       description: Note there are significant differences from the official image and linuxserver.io, please check if your issue is specific to the third-party image.
     validations:
       required: true
+  - type: textarea
+    id: system-status
+    attributes:
+      label: System status
+      description: If available, copy & paste the system status output from Settings > System Status > Copy
+      render: json
   - type: input
     id: browser
     attributes:
       label: Browser
       description: Which browser you are using, if relevant.
       placeholder: e.g. Chrome, Safari
-  - type: input
+  - type: textarea
     id: config-changes
     attributes:
       label: Configuration changes
       description: Any configuration changes you made in `docker-compose.yml`, `docker-compose.env` or `paperless.conf`.
-  - type: input
-    id: other
+  - type: checkboxes
+    id: required-checks
     attributes:
-      label: Other
-      description: Any other relevant details.
+      label: Please confirm the following
+      options:
+        - label: I believe this issue is a bug that affects all users of Paperless-ngx, not something specific to my installation.
+          required: true
+        - label: This issue is not about the OCR or archive creation of a specific file(s). Otherwise, please see above regarding OCR tools.
+          required: true
+        - label: I have already searched for relevant existing issues and discussions before opening this report.
+          required: true
+        - label: I have updated the title field above with a concise description.
+          required: true

.github/PULL_REQUEST_TEMPLATE.md

@@ -8,7 +8,11 @@ Note: All PRs with code changes should be targeted to the `dev` branch, pure doc
 Please include a summary of the change and which issue is fixed (if any) and any relevant motivation / context. List any dependencies that are required for this change. If appropriate, please include an explanation of how your proposed change can be tested. Screenshots and / or videos can also be helpful if appropriate.
 -->
 
-Fixes # (issue)
+<!--
+⚠️ Important: Pull requests that implement a new feature or enhancement *should almost always target an existing feature request* with evidence of community interest and discussion. This is in order to balance the work of implementing and maintaining new features / enhancements. If that is not currently the case, please open a feature request instead of this PR to gather feedback from both users and the project maintainers.
+-->
+
+Closes #(issue or discussion)
 
 ## Type of change
 
@@ -17,14 +21,20 @@ What type of change does your PR introduce to Paperless-ngx?
 NOTE: Please check only one box!
 -->
 
-- [ ] Bug fix (non-breaking change which fixes an issue)
-- [ ] New feature (non-breaking change which adds functionality)
-- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
-- [ ] Other (please explain)
+- [ ] Bug fix: non-breaking change which fixes an issue.
+- [ ] New feature / Enhancement: non-breaking change which adds functionality. _Please read the important note above._
+- [ ] Breaking change: fix or feature that would cause existing functionality to not work as expected.
+- [ ] Documentation only.
+- [ ] Other. Please explain:
 
 ## Checklist:
 
+<!--
+NOTE: PRs that do not address the following will not be merged, please do not skip any relevant items.
+-->
+
 - [ ] I have read & agree with the [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md).
+- [ ] If applicable, I have included testing coverage for new code in this PR, for [backend](https://docs.paperless-ngx.com/development/#testing) and / or [front-end](https://docs.paperless-ngx.com/development/#testing-and-code-style) changes.
 - [ ] If applicable, I have tested my code for new features & regressions on both mobile & desktop devices, using the latest version of major browsers.
 - [ ] If applicable, I have checked that all tests pass, see [documentation](https://docs.paperless-ngx.com/development/#back-end-development).
 - [ ] I have run all `pre-commit` hooks, see [documentation](https://docs.paperless-ngx.com/development/#code-formatting-with-pre-commit-hooks).

.github/dependabot.yml

@@ -8,7 +8,7 @@ updates:
     target-branch: "dev"
     # Look for `package.json` and `lock` files in the `/src-ui` directory
     directory: "/src-ui"
-    # Check the npm registry for updates every month
+    open-pull-requests-limit: 10
     schedule:
       interval: "monthly"
     labels:
@@ -17,6 +17,21 @@ updates:
     # Add reviewers
     reviewers:
       - "paperless-ngx/frontend"
+    groups:
+      frontend-angular-dependencies:
+        patterns:
+          - "@angular*"
+          - "@ng-*"
+          - "ngx-*"
+          - "ng2-pdf-viewer"
+      frontend-jest-dependencies:
+        patterns:
+          - "@types/jest"
+          - "jest*"
+      frontend-eslint-dependencies:
+        patterns:
+          - "@typescript-eslint*"
+          - "eslint"
 
   # Enable version updates for Python
   - package-ecosystem: "pip"
@@ -32,8 +47,26 @@ updates:
     # Add reviewers
     reviewers:
       - "paperless-ngx/backend"
+    ignore:
+      - dependency-name: "uvicorn"
+    groups:
+      development:
+        patterns:
+          - "*pytest*"
+          - "ruff"
+          - "mkdocs-material"
+      django:
+        patterns:
+          - "*django*"
+      major-versions:
+        update-types:
+          - "major"
+      small-changes:
+        update-types:
+          - "minor"
+          - "patch"
 
-  # Enable updates for Github Actions
+  # Enable updates for GitHub Actions
   - package-ecosystem: "github-actions"
     target-branch: "dev"
     directory: "/"
@@ -46,3 +79,9 @@ updates:
     # Add reviewers
     reviewers:
       - "paperless-ngx/ci-cd"
+    groups:
+      actions:
+        update-types:
+          - "major"
+          - "minor"
+          - "patch"

.github/stale.yml

@@ -1,23 +0,0 @@
-# Number of days of inactivity before an issue becomes stale
-daysUntilStale: 30
-
-# Number of days of inactivity before a stale issue is closed
-daysUntilClose: 7
-
-# Only issues or pull requests with any of these labels are check if stale. Defaults to `[]` (disabled)
-any-of-labels: ['cant-reproduce','not a bug','unconfirmed']
-
-# Label to use when marking an issue as stale
-staleLabel: stale
-
-# Comment to post when marking an issue as stale. Set to `false` to disable
-markComment: >
-  This issue has been automatically marked as stale because it has not had
-  recent activity. It will be closed if no further activity occurs. Thank you
-  for your contributions.
-
-# Comment to post when closing a stale issue. Set to `false` to disable
-closeComment: false
-
-# See https://github.com/marketplace/stale for more info on the app
-# and https://github.com/probot/stale for the configuration docs

.github/workflows/ci.yml

@@ -16,41 +16,47 @@ on:
 env:
   # This is the version of pipenv all the steps will use
   # If changing this, change Dockerfile
-  DEFAULT_PIP_ENV_VERSION: "2023.6.12"
-  # This is the default version of Python to use in most steps
-  # If changing this, change Dockerfile
-  DEFAULT_PYTHON_VERSION: "3.9"
+  DEFAULT_PIP_ENV_VERSION: "2024.0.3"
+  # This is the default version of Python to use in most steps which aren't specific
+  DEFAULT_PYTHON_VERSION: "3.11"
 
 jobs:
   pre-commit:
+    # We want to run on external PRs, but not on our own internal PRs as they'll be run
+    # by the push to the branch. Without this if check, checks are duplicated since
+    # internal PRs match both the push and pull_request events.
+    if:
+      github.event_name == 'push' || github.event.pull_request.head.repo.full_name !=
+      github.repository
+
     name: Linting Checks
     runs-on: ubuntu-22.04
     steps:
       -
         name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Install python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
       -
         name: Check files
-        uses: pre-commit/action@v3.0.0
+        uses: pre-commit/action@v3.0.1
 
   documentation:
-    name: "Build Documentation"
+    name: "Build & Deploy Documentation"
     runs-on: ubuntu-22.04
     needs:
       - pre-commit
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
           cache: "pipenv"
@@ -58,7 +64,7 @@ jobs:
       -
         name: Install pipenv
         run: |
-          pip install --user pipenv==${DEFAULT_PIP_ENV_VERSION}
+          pip install --user pipenv==${{ env.DEFAULT_PIP_ENV_VERSION }}
       -
         name: Install dependencies
         run: |
@@ -71,55 +77,44 @@ jobs:
         name: Make documentation
         run: |
           pipenv --python ${{ steps.setup-python.outputs.python-version }} run mkdocs build --config-file ./mkdocs.yml
+      -
+        name: Deploy documentation
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        run: |
+          echo "docs.paperless-ngx.com" > "${{ github.workspace }}/docs/CNAME"
+          git config --global user.name "${{ github.actor }}"
+          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
+          pipenv --python ${{ steps.setup-python.outputs.python-version }} run mkdocs gh-deploy --force --no-history
       -
         name: Upload artifact
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: documentation
           path: site/
           retention-days: 7
 
-  documentation-deploy:
-    name: "Deploy Documentation"
-    runs-on: ubuntu-22.04
-    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-    needs:
-      - documentation
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v3
-      -
-        name: Deploy docs
-        uses: mhausenblas/mkdocs-deploy-gh-pages@master
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CUSTOM_DOMAIN: docs.paperless-ngx.com
-          CONFIG_FILE: mkdocs.yml
-          EXTRA_PACKAGES: build-base
-
   tests-backend:
-    name: "Tests (${{ matrix.python-version }})"
+    name: "Backend Tests (Python ${{ matrix.python-version }})"
     runs-on: ubuntu-22.04
     needs:
       - pre-commit
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10']
+        python-version: ['3.10', '3.11', '3.12']
       fail-fast: false
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Start containers
         run: |
-          docker compose --file ${GITHUB_WORKSPACE}/docker/compose/docker-compose.ci-test.yml pull --quiet
-          docker compose --file ${GITHUB_WORKSPACE}/docker/compose/docker-compose.ci-test.yml up --detach
+          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml pull --quiet
+          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml up --detach
       -
         name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "${{ matrix.python-version }}"
           cache: "pipenv"
@@ -127,7 +122,7 @@ jobs:
       -
         name: Install pipenv
         run: |
-          pip install --user pipenv==${DEFAULT_PIP_ENV_VERSION}
+          pip install --user pipenv==${{ env.DEFAULT_PIP_ENV_VERSION }}
       -
         name: Install system dependencies
         run: |
@@ -158,83 +153,188 @@ jobs:
           cd src/
           pipenv --python ${{ steps.setup-python.outputs.python-version }} run pytest -ra
       -
-        name: Upload coverage to Codecov
+        name: Upload coverage
         if: ${{ matrix.python-version == env.DEFAULT_PYTHON_VERSION }}
-        uses: codecov/codecov-action@v3
+        uses: actions/upload-artifact@v4
         with:
-          # not required for public repos, but intermittently fails otherwise
-          token: ${{ secrets.CODECOV_TOKEN }}
-          # future expansion
-          flags: backend
+          name: backend-coverage-report
+          path: src/coverage.xml
+          retention-days: 7
+          if-no-files-found: warn
       -
         name: Stop containers
         if: always()
         run: |
-          docker compose --file ${GITHUB_WORKSPACE}/docker/compose/docker-compose.ci-test.yml logs
-          docker compose --file ${GITHUB_WORKSPACE}/docker/compose/docker-compose.ci-test.yml down
+          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml logs
+          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml down
 
-  tests-frontend:
-    name: "Tests Frontend"
+  install-frontend-depedendencies:
+    name: "Install Frontend Dependencies"
     runs-on: ubuntu-22.04
     needs:
       - pre-commit
-    strategy:
-      matrix:
-        node-version: [16.x]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       -
-        name: Use Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v3
+        name: Use Node.js 20
+        uses: actions/setup-node@v4
         with:
-          node-version: ${{ matrix.node-version }}
+          node-version: 20.x
           cache: 'npm'
           cache-dependency-path: 'src-ui/package-lock.json'
+      - name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ~/.cache
+          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/package-lock.json') }}
       -
         name: Install dependencies
+        if: steps.cache-frontend-deps.outputs.cache-hit != 'true'
         run: cd src-ui && npm ci
       -
         name: Install Playwright
-        run: npx playwright install --with-deps
+        if: steps.cache-frontend-deps.outputs.cache-hit != 'true'
+        run: cd src-ui && npx playwright install --with-deps
+
+  tests-frontend:
+    name: "Frontend Tests (Node ${{ matrix.node-version }} - ${{ matrix.shard-index }}/${{ matrix.shard-count }})"
+    runs-on: ubuntu-22.04
+    needs:
+      - install-frontend-depedendencies
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [20.x]
+        shard-index: [1, 2, 3, 4]
+        shard-count: [4]
+    steps:
+      - uses: actions/checkout@v4
+      -
+        name: Use Node.js 20
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20.x
+          cache: 'npm'
+          cache-dependency-path: 'src-ui/package-lock.json'
+      - name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ~/.cache
+          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/package-lock.json') }}
+      - name: Re-link Angular cli
+        run: cd src-ui && npm link @angular/cli
       -
         name: Linting checks
         run: cd src-ui && npm run lint
       -
         name: Run Jest unit tests
-        run: cd src-ui && npm run test
+        run: cd src-ui && npm run test -- --max-workers=2 --shard=${{ matrix.shard-index }}/${{ matrix.shard-count }}
       -
         name: Upload Jest coverage
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: jest-coverage-report
-          path: src-ui/coverage
+          name: jest-coverage-report-${{ matrix.shard-index }}
+          path: |
+            src-ui/coverage/coverage-final.json
+            src-ui/coverage/lcov.info
+            src-ui/coverage/clover.xml
           retention-days: 7
+          if-no-files-found: warn
+      -
+        name: Run Playwright e2e tests
+        run: cd src-ui && npx playwright test --shard ${{ matrix.shard-index }}/${{ matrix.shard-count }}
+      -
+        name: Upload Playwright test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-report-${{ matrix.shard-index }}
+          path: src-ui/playwright-report
+          retention-days: 7
+
+  tests-coverage-upload:
+    name: "Upload to Codecov"
+    runs-on: ubuntu-22.04
+    needs:
+      - tests-backend
+      - tests-frontend
+    steps:
+      -
+        uses: actions/checkout@v4
+      -
+        name: Download frontend jest coverage
+        uses: actions/download-artifact@v4
+        with:
+          path: src-ui/coverage/
+          pattern: jest-coverage-report-*
+      -
+        name: Download frontend playwright coverage
+        uses: actions/download-artifact@v4
+        with:
+          path: src-ui/coverage/
+          pattern: playwright-report-*
+          merge-multiple: true
       -
         name: Upload frontend coverage to Codecov
-        if: always()
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
+        with:
+          # not required for public repos, but intermittently fails otherwise
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: frontend
+          directory: src-ui/coverage/
+          # dont include backend coverage files here
+          files: '!coverage.xml'
+      -
+        name: Download backend coverage
+        uses: actions/download-artifact@v4
+        with:
+          name: backend-coverage-report
+          path: src/
+      -
+        name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
         with:
           # not required for public repos, but intermittently fails otherwise
           token: ${{ secrets.CODECOV_TOKEN }}
           # future expansion
-          flags: frontend
+          flags: backend
+          directory: src/
       -
-        name: Run Playwright e2e tests
-        run: cd src-ui && npx playwright test
-      -
-        name: Upload Playwright test results
-        if: always()
-        uses: actions/upload-artifact@v3
+        name: Use Node.js 20
+        uses: actions/setup-node@v4
         with:
-          name: playwright-report
-          path: src-ui/playwright-report
-          retention-days: 7
+          node-version: 20.x
+          cache: 'npm'
+          cache-dependency-path: 'src-ui/package-lock.json'
+      -
+        name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ~/.cache
+          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/package-lock.json') }}
+      -
+        name: Re-link Angular cli
+        run: cd src-ui && npm link @angular/cli
+      -
+        name: Build frontend and upload analysis
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        run: cd src-ui && ng build --configuration=production
 
   build-docker-image:
     name: Build Docker image for ${{ github.ref_name }}
     runs-on: ubuntu-22.04
-    if: github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || contains(github.ref, 'beta.rc') || startsWith(github.ref, 'refs/tags/v'))
+    if: github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || startsWith(github.ref, 'refs/heads/fix-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || contains(github.ref, 'beta.rc') || startsWith(github.ref, 'refs/tags/v'))
     concurrency:
       group: ${{ github.workflow }}-build-docker-image-${{ github.ref_name }}
       cancel-in-progress: true
@@ -252,7 +352,7 @@ jobs:
         #  a tag
         # Otherwise forks would require a Docker Hub account and secrets setup
         run: |
-          if [[ ${{ github.repository_owner }} == "paperless-ngx" && ( ${{ github.ref_name }} == "main" || ${{ github.ref_name }} == "dev" || ${{ github.ref_name }} == "beta" || ${{ startsWith(github.ref, 'refs/tags/v') }} == "true" ) ]] ; then
+          if [[ ${{ github.repository_owner }} == "paperless-ngx" && ( ${{ github.ref_name }} == "dev" || ${{ github.ref_name }} == "beta" || ${{ startsWith(github.ref, 'refs/tags/v') }} == "true" ) ]] ; then
             echo "Enabling DockerHub image push"
             echo "enable=true" >> $GITHUB_OUTPUT
           else
@@ -269,7 +369,7 @@ jobs:
       -
         name: Gather Docker metadata
         id: docker-meta
-        uses: docker/metadata-action@v4
+        uses: docker/metadata-action@v5
         with:
           images: |
             ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}
@@ -284,26 +384,28 @@ jobs:
             type=semver,pattern={{major}}.{{minor}}
       -
         name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       # If https://github.com/docker/buildx/issues/1044 is resolved,
       # the append input with a native arm64 arch could be used to
       # significantly speed up building
       -
         name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
       -
         name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
+        with:
+          platforms: arm64
       -
-        name: Login to Github Container Registry
-        uses: docker/login-action@v2
+        name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
       -
         name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         # Don't attempt to login is not pushing to Docker Hub
         if: steps.push-other-places.outputs.enable == 'true'
         with:
@@ -311,7 +413,7 @@ jobs:
           password: ${{ secrets.DOCKERHUB_TOKEN }}
       -
         name: Login to Quay.io
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         # Don't attempt to login is not pushing to Quay.io
         if: steps.push-other-places.outputs.enable == 'true'
         with:
@@ -320,14 +422,16 @@ jobs:
           password: ${{ secrets.QUAY_ROBOT_TOKEN }}
       -
         name: Build and push
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: ./Dockerfile
-          platforms: linux/amd64,linux/arm/v7,linux/arm64
+          platforms: linux/amd64,linux/arm64
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.docker-meta.outputs.tags }}
           labels: ${{ steps.docker-meta.outputs.labels }}
+          build-args: |
+            PNGX_TAG_VERSION=${{ steps.docker-meta.outputs.version }}
           # Get cache layers from this branch, then dev
           # This allows new branches to get at least some cache benefits, generally from dev
           cache-from: |
@@ -346,24 +450,26 @@ jobs:
           docker cp frontend-extract:/usr/src/paperless/src/documents/static/frontend src/documents/static/frontend/
       -
         name: Upload frontend artifact
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: frontend-compiled
           path: src/documents/static/frontend/
           retention-days: 7
 
   build-release:
+    name: "Build Release"
     needs:
       - build-docker-image
+      - documentation
     runs-on: ubuntu-22.04
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
           cache: "pipenv"
@@ -371,7 +477,7 @@ jobs:
       -
         name: Install pipenv + tools
         run: |
-          pip install --upgrade --user pipenv==${DEFAULT_PIP_ENV_VERSION} setuptools wheel
+          pip install --upgrade --user pipenv==${{ env.DEFAULT_PIP_ENV_VERSION }} setuptools wheel
       -
         name: Install Python dependencies
         run: |
@@ -383,13 +489,13 @@ jobs:
           sudo apt-get install -qq --no-install-recommends gettext liblept5
       -
         name: Download frontend artifact
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: frontend-compiled
           path: src/documents/static/frontend/
       -
         name: Download documentation artifact
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: documentation
           path: docs/_build/html/
@@ -455,13 +561,14 @@ jobs:
           tar -cJf paperless-ngx.tar.xz paperless-ngx/
       -
         name: Upload release artifact
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: release
           path: dist/paperless-ngx.tar.xz
           retention-days: 7
 
   publish-release:
+    name: "Publish Release"
     runs-on: ubuntu-22.04
     outputs:
       prerelease: ${{ steps.get_version.outputs.prerelease }}
@@ -473,7 +580,7 @@ jobs:
     steps:
       -
         name: Download release artifact
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: release
           path: ./
@@ -490,7 +597,7 @@ jobs:
       -
         name: Create Release and Changelog
         id: create-release
-        uses: release-drafter/release-drafter@v5
+        uses: release-drafter/release-drafter@v6
         with:
           name: Paperless-ngx ${{ steps.get_version.outputs.version }}
           tag: ${{ steps.get_version.outputs.version }}
@@ -511,6 +618,7 @@ jobs:
           asset_content_type: application/x-xz
 
   append-changelog:
+    name: "Append Changelog"
     runs-on: ubuntu-22.04
     needs:
       - publish-release
@@ -518,12 +626,12 @@ jobs:
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           ref: main
       -
         name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
           cache: "pipenv"
@@ -531,7 +639,7 @@ jobs:
       -
         name: Install pipenv + tools
         run: |
-          pip install --upgrade --user pipenv==${DEFAULT_PIP_ENV_VERSION} setuptools wheel
+          pip install --upgrade --user pipenv==${{ env.DEFAULT_PIP_ENV_VERSION }} setuptools wheel
       -
         name: Append Changelog to docs
         id: append-Changelog
@@ -541,7 +649,9 @@ jobs:
           git checkout ${{ needs.publish-release.outputs.version }}-changelog
           echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
           echo "Manually linking usernames"
-          sed -i -r 's|@(.+?) \(\[#|[@\1](https://github.com/\1) ([#|ig' changelog-new.md
+          sed -i -r 's|@([a-zA-Z0-9_]+) \(\[#|[@\1](https://github.com/\1) ([#|g' changelog-new.md
+          echo "Removing unneeded comment tags"
+          sed -i -r 's|@<!---->|@|g' changelog-new.md
           CURRENT_CHANGELOG=`tail --lines +2 changelog.md`
           echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
           mv changelog-new.md changelog.md
@@ -552,12 +662,12 @@ jobs:
           git push origin ${{ needs.publish-release.outputs.version }}-changelog
       -
         name: Create Pull Request
-        uses: actions/github-script@v6
+        uses: actions/github-script@v7
         with:
           script: |
             const { repo, owner } = context.repo;
             const result = await github.rest.pulls.create({
-              title: '[Documentation] Add ${{ needs.publish-release.outputs.version }} changelog',
+              title: 'Documentation: Add ${{ needs.publish-release.outputs.version }} changelog',
               owner,
               repo,
               head: '${{ needs.publish-release.outputs.version }}-changelog',

.github/workflows/cleanup-tags.yml

@@ -19,9 +19,13 @@ concurrency:
 
 jobs:
   cleanup-images:
-    name: Cleanup Image Tags for paperless-ngx
+    name: Cleanup Image Tags for ${{ matrix.primary-name }}
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-22.04
+    strategy:
+      fail-fast: false
+      matrix:
+        primary-name: ["paperless-ngx", "paperless-ngx/builder/cache/app"]
     env:
       # Requires a personal access token with the OAuth scope delete:packages
       TOKEN: ${{ secrets.GHA_CONTAINER_DELETE_TOKEN }}
@@ -29,15 +33,15 @@ jobs:
       -
         name: Clean temporary images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/ephemeral@v0.1.0
+        uses: stumpylog/image-cleaner-action/ephemeral@v0.8.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"
           is_org: "true"
-          package_name: "paperless-ngx"
+          package_name: "${{ matrix.primary-name }}"
           scheme: "branch"
           repo_name: "paperless-ngx"
-          match_regex: "feature-"
+          match_regex: "(feature|fix)"
           do_delete: "true"
 
   cleanup-untagged-images:
@@ -49,18 +53,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        include:
-          - primary-name: "paperless-ngx"
-          - primary-name: "paperless-ngx/builder/cache/app"
-          # TODO: Remove the above and replace with the below
-          # - primary-name: "builder/qpdf"
-          # - primary-name: "builder/cache/qpdf"
-          # - primary-name: "builder/pikepdf"
-          # - primary-name: "builder/cache/pikepdf"
-          # - primary-name: "builder/jbig2enc"
-          # - primary-name: "builder/cache/jbig2enc"
-          # - primary-name: "builder/psycopg2"
-          # - primary-name: "builder/cache/psycopg2"
+        primary-name: ["paperless-ngx", "paperless-ngx/builder/cache/app"]
     env:
       # Requires a personal access token with the OAuth scope delete:packages
       TOKEN: ${{ secrets.GHA_CONTAINER_DELETE_TOKEN }}
@@ -68,7 +61,7 @@ jobs:
       -
         name: Clean untagged images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/untagged@v0.1.0
+        uses: stumpylog/image-cleaner-action/untagged@v0.8.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"

.github/workflows/codeql-analysis.yml

@@ -38,11 +38,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -51,4 +51,4 @@ jobs:
         # queries: ./path/to/local/query, your-org/your-repo/queries@main
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3

.github/workflows/crowdin.yml

@@ -0,0 +1,35 @@
+name: Crowdin Action
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '2 */12 * * *'
+  push:
+    paths: [
+      'src/locale/**',
+      'src-ui/messages.xlf',
+      'src-ui/src/locale/**'
+    ]
+    branches: [ dev ]
+
+jobs:
+  synchronize-with-crowdin:
+    name: Crowdin Sync
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+    - name: crowdin action
+      uses: crowdin/github-action@v2
+      with:
+        upload_translations: false
+        download_translations: true
+        crowdin_branch_name: 'dev'
+        localization_branch_name: l10n_dev
+        pull_request_labels: 'skip-changelog, translation'
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        CROWDIN_PROJECT_ID: ${{ secrets.CROWDIN_PROJECT_ID }}
+        CROWDIN_PERSONAL_TOKEN: ${{ secrets.CROWDIN_PERSONAL_TOKEN }}

.github/workflows/project-actions.yml

@@ -1,10 +1,6 @@
 name: Project Automations
 
 on:
-  issues:
-    types:
-      - opened
-      - reopened
   pull_request_target: #_target allows access to secrets
     types:
       - opened
@@ -16,25 +12,7 @@ on:
 permissions:
   contents: read
 
-env:
-  todo: Todo
-  done: Done
-  in_progress: In Progress
-
 jobs:
-  issue_opened_or_reopened:
-    name: issue_opened_or_reopened
-    runs-on: ubuntu-22.04
-    if: github.event_name == 'issues' && (github.event.action == 'opened' || github.event.action == 'reopened')
-    steps:
-      - name: Add issue to project and set status to ${{ env.todo }}
-        uses: leonsteinhaeuser/project-beta-automations@v2.1.0
-        with:
-          gh_token: ${{ secrets.GH_TOKEN }}
-          organization: paperless-ngx
-          project_id: 2
-          resource_node_id: ${{ github.event.issue.node_id }}
-          status_value: ${{ env.todo }} # Target status
   pr_opened_or_reopened:
     name: pr_opened_or_reopened
     runs-on: ubuntu-22.04
@@ -43,15 +21,7 @@ jobs:
       pull-requests: write
     if: github.event_name == 'pull_request_target' && (github.event.action == 'opened' || github.event.action == 'reopened') && github.event.pull_request.user.login != 'dependabot'
     steps:
-      - name: Add PR to project and set status to "Needs Review"
-        uses: leonsteinhaeuser/project-beta-automations@v2.1.0
-        with:
-          gh_token: ${{ secrets.GH_TOKEN }}
-          organization: paperless-ngx
-          project_id: 2
-          resource_node_id: ${{ github.event.pull_request.node_id }}
-          status_value: "Needs Review" # Target status
       - name: Label PR with release-drafter
-        uses: release-drafter/release-drafter@v5
+        uses: release-drafter/release-drafter@v6
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/repo-maintenance.yml

@@ -8,6 +8,7 @@ on:
 permissions:
   issues: write
   pull-requests: write
+  discussions: write
 
 concurrency:
   group: lock
@@ -15,33 +16,279 @@ concurrency:
 jobs:
   stale:
     name: 'Stale'
+    if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v8
+      - uses: actions/stale@v9
         with:
-          days-before-stale: 30
-          days-before-close: 7
-          only-labels: 'cant-reproduce'
+          days-before-stale: 7
+          days-before-close: 14
+          any-of-labels: 'stale,cant-reproduce,not a bug'
           stale-issue-label: stale
           stale-pr-label: stale
           stale-issue-message: >
             This issue has been automatically marked as stale because it has not had
             recent activity. It will be closed if no further activity occurs. Thank you
-            for your contributions.
+            for your contributions. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
   lock-threads:
     name: 'Lock Old Threads'
+    if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-latest
     steps:
-      - uses: dessant/lock-threads@v4
+      - uses: dessant/lock-threads@v5
         with:
           issue-inactive-days: '30'
           pr-inactive-days: '30'
+          discussion-inactive-days: '30'
           log-output: true
           issue-comment: >
             This issue has been automatically locked since there
             has not been any recent activity after it was closed.
             Please open a new discussion or issue for related concerns.
+            See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
           pr-comment: >
             This pull request has been automatically locked since there
             has not been any recent activity after it was closed.
             Please open a new discussion or issue for related concerns.
+            See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
+          discussion-comment: >
+            This discussion has been automatically locked since there
+            has not been any recent activity after it was closed.
+            Please open a new discussion for related concerns.
+            See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
+  close-answered-discussions:
+    name: 'Close Answered Discussions'
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/github-script@v7
+        with:
+          script: |
+            function sleep(ms) {
+              return new Promise(resolve => setTimeout(resolve, ms));
+            }
+
+            const query = `query($owner:String!, $name:String!) {
+              repository(owner:$owner, name:$name){
+                discussions(first:100, answered:true, states:[OPEN]) {
+                  nodes {
+                    id,
+                    number
+                  }
+                }
+              }
+            }`;
+            const variables = {
+              owner: context.repo.owner,
+              name: context.repo.repo,
+            }
+            const result = await github.graphql(query, variables)
+
+            console.log(`Found ${result.repository.discussions.nodes.length} open answered discussions`)
+
+            for (const discussion of result.repository.discussions.nodes) {
+              console.log(`Closing discussion #${discussion.number} (${discussion.id})`)
+
+              const addCommentMutation = `mutation($discussion:ID!, $body:String!) {
+                addDiscussionComment(input:{discussionId:$discussion, body:$body}) {
+                  clientMutationId
+                }
+              }`;
+              const commentVariables = {
+                discussion: discussion.id,
+                body: 'This discussion has been automatically closed because it was marked as answered. Please see our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.',
+              }
+              await github.graphql(addCommentMutation, commentVariables)
+
+              const closeDiscussionMutation = `mutation($discussion:ID!, $reason:DiscussionCloseReason!) {
+                closeDiscussion(input:{discussionId:$discussion, reason:$reason}) {
+                  clientMutationId
+                }
+              }`;
+              const closeVariables = {
+                discussion: discussion.id,
+                reason: "RESOLVED",
+              }
+              await github.graphql(closeDiscussionMutation, closeVariables)
+
+              await sleep(1000)
+            }
+  close-outdated-discussions:
+    name: 'Close Outdated Discussions'
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/github-script@v7
+        with:
+          script: |
+            function sleep(ms) {
+              return new Promise(resolve => setTimeout(resolve, ms));
+            }
+
+            const CUTOFF_DAYS = 180;
+            const cutoff = new Date();
+            cutoff.setDate(cutoff.getDate() - CUTOFF_DAYS);
+
+            const query = `query(
+                $owner:String!,
+                $name:String!,
+                $supportCategory:ID!,
+                $generalCategory:ID!,
+              ) {
+              supportDiscussions: repository(owner:$owner, name:$name){
+                discussions(
+                  categoryId:$supportCategory,
+                  last:50,
+                  answered:false,
+                  states:[OPEN],
+                ) {
+                  nodes {
+                    id,
+                    number,
+                    updatedAt
+                  }
+                },
+              },
+              generalDiscussions: repository(owner:$owner, name:$name){
+                discussions(
+                  categoryId:$generalCategory,
+                  last:50,
+                  states:[OPEN],
+                ) {
+                  nodes {
+                    id,
+                    number,
+                    updatedAt
+                  }
+                }
+              }
+            }`;
+            const variables = {
+              owner: context.repo.owner,
+              name: context.repo.repo,
+              supportCategory: "DIC_kwDOG1Zs184CBKWK",
+              generalCategory: "DIC_kwDOG1Zs184CBKWJ"
+            }
+            const result = await github.graphql(query, variables);
+            const combinedDiscussions = [
+              ...result.supportDiscussions.discussions.nodes,
+              ...result.generalDiscussions.discussions.nodes,
+            ]
+
+            console.log(`Checking ${combinedDiscussions.length} open discussions`);
+
+            for (const discussion of combinedDiscussions) {
+              if (new Date(discussion.updatedAt) < cutoff) {
+                console.log(`Closing outdated discussion #${discussion.number} (${discussion.id}), last updated at ${discussion.updatedAt}`);
+                const addCommentMutation = `mutation($discussion:ID!, $body:String!) {
+                  addDiscussionComment(input:{discussionId:$discussion, body:$body}) {
+                    clientMutationId
+                  }
+                }`;
+                const commentVariables = {
+                  discussion: discussion.id,
+                  body: 'This discussion has been automatically closed due to inactivity. Please see our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.',
+                }
+                await github.graphql(addCommentMutation, commentVariables);
+
+                const closeDiscussionMutation = `mutation($discussion:ID!, $reason:DiscussionCloseReason!) {
+                  closeDiscussion(input:{discussionId:$discussion, reason:$reason}) {
+                    clientMutationId
+                  }
+                }`;
+                const closeVariables = {
+                  discussion: discussion.id,
+                  reason: "OUTDATED",
+                }
+                await github.graphql(closeDiscussionMutation, closeVariables);
+
+                await sleep(1000);
+              }
+            }
+  close-unsupported-feature-requests:
+    name: 'Close Unsupported Feature Requests'
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/github-script@v7
+        with:
+          script: |
+            function sleep(ms) {
+              return new Promise(resolve => setTimeout(resolve, ms));
+            }
+
+            const CUTOFF_MAX_COUNT = 80;
+            const CUTOFF_1_DAYS = 180;
+            const CUTOFF_1_COUNT = 5;
+            const CUTOFF_2_DAYS = 365;
+            const CUTOFF_2_COUNT = 20;
+            const CUTOFF_3_DAYS = 730;
+            const CUTOFF_3_COUNT = 40;
+
+            const cutoff1Date = new Date();
+            cutoff1Date.setDate(cutoff1Date.getDate() - CUTOFF_1_DAYS);
+            const cutoff2Date = new Date();
+            cutoff2Date.setDate(cutoff2Date.getDate() - CUTOFF_2_DAYS);
+            const cutoff3Date = new Date();
+            cutoff3Date.setDate(cutoff3Date.getDate() - CUTOFF_3_DAYS);
+
+            const query = `query(
+                $owner:String!,
+                $name:String!,
+                $featureRequestsCategory:ID!,
+              ) {
+              repository(owner:$owner, name:$name){
+                discussions(
+                  categoryId:$featureRequestsCategory,
+                  last:100,
+                  states:[OPEN],
+                ) {
+                  nodes {
+                    id,
+                    number,
+                    updatedAt,
+                    upvoteCount,
+                  }
+                },
+              }
+            }`;
+            const variables = {
+              owner: context.repo.owner,
+              name: context.repo.repo,
+              featureRequestsCategory: "DIC_kwDOG1Zs184CBNr4"
+            }
+            const result = await github.graphql(query, variables);
+
+            for (const discussion of result.repository.discussions.nodes) {
+              const discussionUpdatedDate = new Date(discussion.updatedAt);
+              const discussionCreatedDate = new Date(discussion.createdAt);
+              if ((discussionUpdatedDate < cutoff1Date && discussion.upvoteCount < CUTOFF_MAX_COUNT) ||
+                  (discussionCreatedDate < cutoff1Date && discussion.upvoteCount < CUTOFF_1_COUNT) ||
+                  (discussionCreatedDate < cutoff2Date && discussion.upvoteCount < CUTOFF_2_COUNT) ||
+                  (discussionCreatedDate < cutoff3Date && discussion.upvoteCount < CUTOFF_3_COUNT)) {
+                console.log(`Closing discussion #${discussion.number} (${discussion.id}), last updated at ${discussion.updatedAt} with votes ${discussion.upvoteCount}`);
+                const addCommentMutation = `mutation($discussion:ID!, $body:String!) {
+                  addDiscussionComment(input:{discussionId:$discussion, body:$body}) {
+                    clientMutationId
+                  }
+                }`;
+                const commentVariables = {
+                  discussion: discussion.id,
+                  body: 'This discussion has been automatically closed due to lack of community support. Please see our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.',
+                }
+                await github.graphql(addCommentMutation, commentVariables);
+
+                const closeDiscussionMutation = `mutation($discussion:ID!, $reason:DiscussionCloseReason!) {
+                  closeDiscussion(input:{discussionId:$discussion, reason:$reason}) {
+                    clientMutationId
+                  }
+                }`;
+                const closeVariables = {
+                  discussion: discussion.id,
+                  reason: "OUTDATED",
+                }
+                await github.graphql(closeDiscussionMutation, closeVariables);
+
+                await sleep(1000);
+              }
+            }

.gitignore

@@ -22,6 +22,7 @@ var/
 *.egg-info/
 .installed.cfg
 *.egg
+/src/paperless_mail/templates/node_modules
 
 # PyInstaller
 #  Usually these files are written by a python script from a template
@@ -65,6 +66,8 @@ target/
 .vscode
 /src-ui/.vscode
 /docs/.vscode
+.vscode-server
+*CommandMarker
 
 # Other stuff that doesn't belong
 .virtualenv

.pre-commit-config.yaml

@@ -5,12 +5,14 @@
 repos:
   # General hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.6.0
     hooks:
       - id: check-docstring-first
       - id: check-json
         exclude: "tsconfig.*json"
       - id: check-yaml
+        args:
+          - "--unsafe"
       - id: check-toml
       - id: check-executables-have-shebangs
       - id: end-of-file-fixer
@@ -26,8 +28,17 @@ repos:
           - svg
       - id: check-case-conflict
       - id: detect-private-key
-  - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: 'v2.7.1'
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        exclude: "(^src-ui/src/locale/)|(^src-ui/e2e/)|(^src/paperless_mail/tests/samples/)"
+        exclude_types:
+          - pofile
+          - json
+  # See https://github.com/prettier/prettier/issues/15742 for the fork reason
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: 'v3.3.3'
     hooks:
       - id: prettier
         types_or:
@@ -36,17 +47,14 @@ repos:
           - markdown
         exclude: "(^Pipfile\\.lock$)"
   # Python hooks
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.272'
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: 'v0.6.8'
     hooks:
       - id: ruff
-  - repo: https://github.com/psf/black
-    rev: 23.3.0
-    hooks:
-      - id: black
+      - id: ruff-format
   # Dockerfile hooks
   - repo: https://github.com/AleksaC/hadolint-py
-    rev: v2.12.0.2
+    rev: v2.12.0.3
     hooks:
       - id: hadolint
   # Shell script hooks
@@ -54,9 +62,11 @@ repos:
     rev: v6.2.1
     hooks:
       - id: beautysh
+        additional_dependencies:
+          - setuptools
         args:
           - "--tab"
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: "v0.9.0.5"
+    rev: "v0.10.0.1"
     hooks:
       - id: shellcheck

.prettierrc

@@ -1,4 +1,16 @@
-# https://prettier.io/docs/en/options.html#semicolons
-semi: false
-# https://prettier.io/docs/en/options.html#quotes
-singleQuote: true
+{
+    # https://prettier.io/docs/en/options.html#semicolons
+    "semi": false,
+    # https://prettier.io/docs/en/options.html#quotes
+    "singleQuote": true,
+    # https://prettier.io/docs/en/options.html#trailing-commas
+    "trailingComma": "es5",
+    "overrides": [
+        {
+            "files": ["docs/*.md"],
+            "options": {
+                "tabWidth": 4,
+            }
+        }
+    ]
+}

.python-version

@@ -1 +1 @@
-3.8.16
+3.10.15

.ruff.toml

@@ -1,23 +1,47 @@
-# https://beta.ruff.rs/docs/settings/
-# https://beta.ruff.rs/docs/rules/
-extend-select = ["I", "W", "UP", "COM", "DJ", "EXE", "ISC", "ICN", "G201", "INP", "PIE", "RSE", "SIM", "TID", "PLC", "PLE", "RUF"]
-# TODO PTH
-ignore = ["DJ001", "SIM105"]
 fix = true
 line-length = 88
 respect-gitignore = true
 src = ["src"]
-target-version = "py38"
-format = "grouped"
+target-version = "py310"
+output-format = "grouped"
 show-fixes = true
 
-[per-file-ignores]
+# https://docs.astral.sh/ruff/settings/
+# https://docs.astral.sh/ruff/rules/
+[lint]
+extend-select = [
+  "W",     # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
+  "I",     # https://docs.astral.sh/ruff/rules/#isort-i
+  "UP",    # https://docs.astral.sh/ruff/rules/#pyupgrade-up
+  "COM",   # https://docs.astral.sh/ruff/rules/#flake8-commas-com
+  "DJ",    # https://docs.astral.sh/ruff/rules/#flake8-django-dj
+  "EXE",   # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
+  "ISC",   # https://docs.astral.sh/ruff/rules/#flake8-implicit-str-concat-isc
+  "ICN",   # https://docs.astral.sh/ruff/rules/#flake8-import-conventions-icn
+  "G201",  # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
+  "INP",   # https://docs.astral.sh/ruff/rules/#flake8-no-pep420-inp
+  "PIE",   # https://docs.astral.sh/ruff/rules/#flake8-pie-pie
+  "Q",     # https://docs.astral.sh/ruff/rules/#flake8-quotes-q
+  "RSE",   # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
+  "T20",   # https://docs.astral.sh/ruff/rules/#flake8-print-t20
+  "SIM",   # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
+  "TID",   # https://docs.astral.sh/ruff/rules/#flake8-tidy-imports-tid
+  "TCH",   # https://docs.astral.sh/ruff/rules/#flake8-type-checking-tch
+  "PLC",   # https://docs.astral.sh/ruff/rules/#pylint-pl
+  "PLE",   # https://docs.astral.sh/ruff/rules/#pylint-pl
+  "RUF",   # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
+  "FLY",   # https://docs.astral.sh/ruff/rules/#flynt-fly
+]
+# TODO PTH https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
+ignore = ["DJ001", "SIM105", "RUF012"]
+
+[lint.per-file-ignores]
 ".github/scripts/*.py" = ["E501", "INP001", "SIM117"]
-"docker/wait-for-redis.py" = ["INP001"]
+"docker/wait-for-redis.py" = ["INP001", "T201"]
 "*/tests/*.py" = ["E501", "SIM117"]
-"*/migrations/*.py" = ["E501", "SIM"]
+"*/migrations/*.py" = ["E501", "SIM", "T201"]
 "src/paperless_tesseract/tests/test_parser.py" = ["RUF001"]
 "src/documents/models.py" = ["SIM115"]
 
-[isort]
+[lint.isort]
 force-single-line = true

CODE_OF_CONDUCT.md

@@ -5,7 +5,7 @@
 We as members, contributors, and leaders pledge to make participation in our
 community a harassment-free experience for everyone, regardless of age, body
 size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
+identity and expression, level of experience, education, socioeconomic status,
 nationality, personal appearance, race, religion, or sexual identity
 and orientation.
 

CONTRIBUTING.md

@@ -11,7 +11,7 @@ If you want to implement something big:
 
 ## Python
 
-Paperless supports python 3.8 and 3.9. We format Python code with [Black](https://github.com/psf/black).
+Paperless supports python 3.10 - 3.12 at this time. We format Python code with [ruff](https://docs.astral.sh/ruff/formatter/).
 
 ## Branches
 
@@ -45,7 +45,7 @@ Examples of `non-trivial` PRs might include:
 
 - Additional features
 - Large changes to many distinct files
-- Breaking or depreciation of existing features
+- Breaking or deprecation of existing features
 
 Our community review process for `non-trivial` PRs is the following:
 
@@ -58,6 +58,13 @@ Our community review process for `non-trivial` PRs is the following:
 
 This process might be slow as community members have different schedules and time to dedicate to the Paperless project. However it ensures community code reviews are as brilliantly thorough as they once were with @jonaswinkler.
 
+# AI-Generated Code
+
+This project does not specifically prohibit the use of AI-generated code _during the process_ of creating a PR, however:
+
+1. Any code present in the final PR that was generated using AI sources should be clearly attributed as such and must not violate copyright protections.
+2. We will not accept PRs that are entirely or mostly AI-derived.
+
 # Translating Paperless-ngx
 
 Some notes about translation:
@@ -87,7 +94,7 @@ The following files need to be changed:
 
 - src-ui/angular.json (under the _projects/paperless-ui/i18n/locales_ JSON key)
 - src/paperless/settings.py (in the _LANGUAGES_ array)
-- src-ui/src/app/services/settings.service.ts (inside the _getLanguageOptions_ method)
+- src-ui/src/app/services/settings.service.ts (inside the _LANGUAGE_OPTIONS_ array)
 - src-ui/src/app/app.module.ts (import locale from _angular/common/locales_ and call _registerLocaleData_)
 
 Please add the language in the correct order, alphabetically by locale.
@@ -130,3 +137,19 @@ All team members are notified when mentioned or assigned to a relevant issue or
 We are not overly strict with inviting people to the organization. If you have read the [team permissions](#permissions) and think having additional access would enhance your contributions, please reach out to an [admin](#structure) of the team.
 
 The admins occasionally invite contributors directly if we believe having them on a team will accelerate their work.
+
+# Automatic Repository Maintenance
+
+The Paperless-ngx team appreciates all effort and interest from the community in filing bug reports, creating feature requests, sharing ideas and helping other
+community members. That said, in an effort to keep the repository organized and managebale the project uses automatic handling of certain areas:
+
+- Issues that cannot be reproduced will be marked 'stale' after 7 days of inactivity and closed after 14 further days of inactivity.
+- Issues, pull requests and discussions that are closed will be locked after 30 days of inactivity.
+- Discussions with a marked answer will be automatically closed.
+- Discussions in the 'General' or 'Support' categories will be closed after 180 days of inactivity.
+- Feature requests that do not meet the following thresholds will be closed: 180 days of inactivity, < 5 "up-votes" after 180 days, < 20 "up-votes" after 1 year or < 80 "up-votes" at 2 years.
+
+In all cases, threads can be re-opened by project maintainers and, of course, users can always create a new discussion for related concerns.
+Finally, remember that all information remains searchable and 'closed' feature requests can still serve as inspiration for new features.
+
+Thank you all for your contributions.

Dockerfile

@@ -5,14 +5,24 @@
 # Purpose: Compiles the frontend
 # Notes:
 #  - Does NPM stuff with Typescript and such
-FROM --platform=$BUILDPLATFORM docker.io/node:16-bookworm-slim AS compile-frontend
+FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-slim AS compile-frontend
 
 COPY ./src-ui /src/src-ui
 
 WORKDIR /src/src-ui
 RUN set -eux \
   && npm update npm -g \
-  && npm ci --omit=optional
+  && npm ci
+
+ARG PNGX_TAG_VERSION=
+# Add the tag to the environment file if its a tagged dev build
+RUN set -eux && \
+case "${PNGX_TAG_VERSION}" in \
+  dev|beta|fix*|feature*) \
+    sed -i -E "s/version: '([0-9\.]+)'/version: '\1 #${PNGX_TAG_VERSION}'/g" /src/src-ui/src/environments/environment.prod.ts \
+    ;; \
+esac
+
 RUN set -eux \
   && ./node_modules/.bin/ng build --configuration production
 
@@ -21,7 +31,7 @@ RUN set -eux \
 # Comments:
 #  - pipenv dependencies are not left in the final image
 #  - pipenv can't touch the final image somehow
-FROM --platform=$BUILDPLATFORM docker.io/python:3.9-alpine as pipenv-base
+FROM --platform=$BUILDPLATFORM docker.io/python:3.12-alpine AS pipenv-base
 
 WORKDIR /usr/src/pipenv
 
@@ -29,7 +39,7 @@ COPY Pipfile* ./
 
 RUN set -eux \
   && echo "Installing pipenv" \
-    && python3 -m pip install --no-cache-dir --upgrade pipenv==2023.6.12 \
+    && python3 -m pip install --no-cache-dir --upgrade pipenv==2024.0.3 \
   && echo "Generating requirement.txt" \
     && pipenv requirements > requirements.txt
 
@@ -37,7 +47,7 @@ RUN set -eux \
 # Purpose: The final image
 # Comments:
 #  - Don't leave anything extra in here
-FROM docker.io/python:3.9-slim-bookworm as main-app
+FROM docker.io/python:3.12-slim-bookworm AS main-app
 
 LABEL org.opencontainers.image.authors="paperless-ngx team <hello@paperless-ngx.com>"
 LABEL org.opencontainers.image.documentation="https://docs.paperless-ngx.com/"
@@ -47,6 +57,21 @@ LABEL org.opencontainers.image.licenses="GPL-3.0-only"
 
 ARG DEBIAN_FRONTEND=noninteractive
 
+# Buildx provided, must be defined to use though
+ARG TARGETARCH
+
+# Can be workflow provided, defaults set for manual building
+ARG JBIG2ENC_VERSION=0.29
+ARG QPDF_VERSION=11.9.0
+ARG GS_VERSION=10.03.1
+
+# Set Python environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    # Ignore warning from Whitenoise
+    PYTHONWARNINGS="ignore:::django.http.response:517" \
+    PNGX_CONTAINERIZED=1
+
 #
 # Begin installation and configuration
 # Order the steps below from least often changed to most
@@ -67,23 +92,10 @@ ARG RUNTIME_PACKAGES="\
   gnupg \
   icc-profiles-free \
   imagemagick \
-  # Image processing
-  liblept5 \
-  liblcms2-2 \
-  libtiff6 \
-  libfreetype6 \
-  libwebp7 \
-  libopenjp2-7 \
-  libimagequant0 \
-  libraqm0 \
-  libjpeg62-turbo \
   # PostgreSQL
-  libpq5 \
   postgresql-client \
   # MySQL / MariaDB
   mariadb-client \
-  # For Numpy
-  libatlas3-base \
   # OCRmyPDF dependencies
   tesseract-ocr \
   tesseract-ocr-eng \
@@ -93,12 +105,11 @@ ARG RUNTIME_PACKAGES="\
   tesseract-ocr-spa \
   unpaper \
   pngquant \
-  # pikepdf / qpdf
   jbig2dec \
+  # lxml
   libxml2 \
   libxslt1.1 \
-  libgnutls30 \
-  libqpdf29 \
+  # itself
   qpdf \
   # Mime type detection
   file \
@@ -107,9 +118,7 @@ ARG RUNTIME_PACKAGES="\
   zlib1g \
   # Barcode splitter
   libzbar0 \
-  poppler-utils \
-  # RapidFuzz on armv7
-  libatomic1"
+  poppler-utils"
 
 # Install basic runtime packages.
 # These change very infrequently
@@ -117,7 +126,37 @@ RUN set -eux \
   echo "Installing system packages" \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES} \
-    && rm -rf /var/lib/apt/lists/* \
+    && echo "Installing pre-built updates" \
+      && echo "Installing qpdf ${QPDF_VERSION}" \
+        && curl --fail --silent --show-error --location \
+          --output libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        && curl --fail --silent --show-error --location \
+          --output qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && echo "Installing Ghostscript ${GS_VERSION}" \
+        && curl --fail --silent --show-error --location \
+          --output libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        && curl --fail --silent --show-error --location \
+          --output ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        && curl --fail --silent --show-error --location \
+          --output libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+      && echo "Installing jbig2enc" \
+        && curl --fail --silent --show-error --location \
+          --output jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+        && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+      && echo "Cleaning up image layer" \
+        && rm --force --verbose *.deb \
+    && rm --recursive --force --verbose /var/lib/apt/lists/* \
   && echo "Installing supervisor" \
     && python3 -m pip install --default-timeout=1000 --upgrade --no-cache-dir supervisor==4.2.5
 
@@ -164,45 +203,10 @@ RUN set -eux \
     && chmod 755 /usr/local/bin/paperless_cmd.sh \
     && mv flower-conditional.sh /usr/local/bin/flower-conditional.sh \
     && chmod 755 /usr/local/bin/flower-conditional.sh \
-  && echo "Installing managment commands" \
+  && echo "Installing management commands" \
     && chmod +x install_management_commands.sh \
     && ./install_management_commands.sh
 
-# Buildx provided, must be defined to use though
-ARG TARGETARCH
-ARG TARGETVARIANT
-
-# Can be workflow provided, defaults set for manual building
-ARG JBIG2ENC_VERSION=0.29
-ARG QPDF_VERSION=11.3.0
-ARG PIKEPDF_VERSION=7.2.0
-ARG PSYCOPG2_VERSION=2.9.6
-
-# Install the built packages from the installer library images
-# These change sometimes
-RUN set -eux \
-  && echo "Getting binaries" \
-    && mkdir paperless-ngx \
-    && curl --fail --silent --show-error --output paperless-ngx.tar.gz --location https://github.com/paperless-ngx/builder/archive/58bb061b9b3b63009852d6d875f9a305d9ae6ac9.tar.gz \
-    && tar -xf paperless-ngx.tar.gz --directory paperless-ngx --strip-components=1 \
-    && cd paperless-ngx \
-    # Setting a specific revision ensures we know what this installed
-    # and ensures cache breaking on changes
-  && echo "Installing jbig2enc" \
-    && cp ./jbig2enc/${JBIG2ENC_VERSION}/${TARGETARCH}${TARGETVARIANT}/jbig2 /usr/local/bin/ \
-    && cp ./jbig2enc/${JBIG2ENC_VERSION}/${TARGETARCH}${TARGETVARIANT}/libjbig2enc* /usr/local/lib/ \
-    && chmod a+x /usr/local/bin/jbig2 \
-  && echo "Installing pikepdf and dependencies" \
-    && python3 -m pip install --no-cache-dir ./pikepdf/${PIKEPDF_VERSION}/${TARGETARCH}${TARGETVARIANT}/*.whl \
-    && python3 -m pip list \
-  && echo "Installing psycopg2" \
-    && python3 -m pip install --no-cache-dir ./psycopg2/${PSYCOPG2_VERSION}/${TARGETARCH}${TARGETVARIANT}/psycopg2*.whl \
-    && python3 -m pip list \
-  && echo "Cleaning up image layer" \
-    && cd ../ \
-    && rm -rf paperless-ngx \
-    && rm paperless-ngx.tar.gz
-
 WORKDIR /usr/src/paperless/src/
 
 # Python dependencies
@@ -214,7 +218,11 @@ COPY --from=pipenv-base /usr/src/pipenv/requirements.txt ./
 ARG BUILD_PACKAGES="\
   build-essential \
   git \
-  default-libmysqlclient-dev"
+  # https://www.psycopg.org/docs/install.html#prerequisites
+  libpq-dev \
+  # https://github.com/PyMySQL/mysqlclient#linux
+  default-libmysqlclient-dev \
+  pkg-config"
 
 # hadolint ignore=DL3042
 RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
@@ -224,35 +232,52 @@ RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
     && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
     && python3 -m pip install --no-cache-dir --upgrade wheel \
   && echo "Installing Python requirements" \
-    && python3 -m pip install --default-timeout=1000 --requirement requirements.txt \
+    && curl --fail --silent --show-error --location \
+    --output psycopg_c-3.2.2-cp312-cp312-linux_x86_64.whl \
+    https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.2/psycopg_c-3.2.2-cp312-cp312-linux_x86_64.whl \
+    && curl --fail --silent --show-error --location \
+    --output psycopg_c-3.2.2-cp312-cp312-linux_aarch64.whl  \
+    https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.2/psycopg_c-3.2.2-cp312-cp312-linux_aarch64.whl \
+    && python3 -m pip install --default-timeout=1000 --find-links . --requirement requirements.txt \
   && echo "Installing NLTK data" \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \
-    && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt \
+    && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt_tab \
   && echo "Cleaning up image" \
-    && apt-get -y purge ${BUILD_PACKAGES} \
-    && apt-get -y autoremove --purge \
+    && apt-get --yes purge ${BUILD_PACKAGES} \
+    && apt-get --yes autoremove --purge \
     && apt-get clean --yes \
-    && rm -rf /var/lib/apt/lists/* \
-    && rm -rf /tmp/* \
-    && rm -rf /var/tmp/* \
-    && rm -rf /var/cache/apt/archives/* \
-    && truncate -s 0 /var/log/*log
+    && rm --recursive --force --verbose *.whl \
+    && rm --recursive --force --verbose /var/lib/apt/lists/* \
+    && rm --recursive --force --verbose /tmp/* \
+    && rm --recursive --force --verbose /var/tmp/* \
+    && rm --recursive --force --verbose /var/cache/apt/archives/* \
+    && truncate --size 0 /var/log/*log
 
 # copy backend
-COPY ./src ./
+COPY --chown=1000:1000 ./src ./
 
 # copy frontend
-COPY --from=compile-frontend /src/src/documents/static/frontend/ ./documents/static/frontend/
+COPY --from=compile-frontend --chown=1000:1000 /src/src/documents/static/frontend/ ./documents/static/frontend/
 
 # add users, setup scripts
 # Mount the compiled frontend to expected location
 RUN set -eux \
-  && addgroup --gid 1000 paperless \
-  && useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
-  && chown -R paperless:paperless /usr/src/paperless \
-  && gosu paperless python3 manage.py collectstatic --clear --no-input --link \
-  && gosu paperless python3 manage.py compilemessages
+  && echo "Setting up user/group" \
+    && addgroup --gid 1000 paperless \
+    && useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
+  && echo "Creating volume directories" \
+    && mkdir --parents --verbose /usr/src/paperless/data \
+    && mkdir --parents --verbose /usr/src/paperless/media \
+    && mkdir --parents --verbose /usr/src/paperless/consume \
+    && mkdir --parents --verbose /usr/src/paperless/export \
+  && echo "Creating gnupg directory" \
+    && mkdir -m700 --verbose /usr/src/paperless/.gnupg \
+  && echo "Adjusting all permissions" \
+    && chown --from root:root --changes --recursive paperless:paperless /usr/src/paperless \
+  && echo "Collecting static files" \
+    && gosu paperless python3 manage.py collectstatic --clear --no-input --link \
+    && gosu paperless python3 manage.py compilemessages
 
 VOLUME ["/usr/src/paperless/data", \
         "/usr/src/paperless/media", \
@@ -264,3 +289,5 @@ ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
 EXPOSE 8000
 
 CMD ["/usr/local/bin/paperless_cmd.sh"]
+
+HEALTHCHECK --interval=30s --timeout=10s --retries=5 CMD [ "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000" ]

Pipfile

@@ -3,77 +3,70 @@ url = "https://pypi.python.org/simple"
 verify_ssl = true
 name = "pypi"
 
-[[source]]
-url = "https://www.piwheels.org/simple"
-verify_ssl = true
-name = "piwheels"
-
 [packages]
-dateparser = "~=1.1"
+dateparser = "~=1.2"
 # WARNING: django does not use semver.
 #          Only patch versions are guaranteed to not introduce breaking changes.
-django = "~=4.1.9"
-django-cors-headers = "*"
+django = "~=5.1.1"
+django-allauth = {extras = ["socialaccount"], version = "*"}
+django-auditlog = "*"
 django-celery-results = "*"
 django-compression-middleware = "*"
-django-guardian = "*"
+django-cors-headers = "*"
 django-extensions = "*"
-django-filter = "~=22.1"
-djangorestframework = "~=3.14"
+django-filter = "~=24.3"
+django-guardian = "*"
+django-multiselectfield = "*"
+django-soft-delete = "*"
+djangorestframework = "==3.15.2"
 djangorestframework-guardian = "*"
+drf-writable-nested = "*"
+bleach = "*"
+celery = {extras = ["redis"], version = "*"}
+channels = "~=4.1"
+channels-redis = "*"
+concurrent-log-handler = "*"
 filelock = "*"
+flower = "*"
+gotenberg-client = "*"
 gunicorn = "*"
+httpx-oauth = "*"
 imap-tools = "*"
+inotifyrecursive = "~=0.3"
+jinja2 = "~=3.1"
 langdetect = "*"
+mysqlclient = "*"
+nltk = "*"
+ocrmypdf = "~=16.5"
 pathvalidate = "*"
-pillow = "*"
-pikepdf = "*"
-python-gnupg = "*"
-python-dotenv = "*"
+pdf2image = "*"
+psycopg = {version = "*", extras = ["c"]}
 python-dateutil = "*"
-python-magic = "*"
+python-dotenv = "*"
+python-gnupg = "*"
 python-ipware = "*"
-psycopg2 = "*"
+python-magic = "*"
+pyzbar = "*"
 rapidfuzz = "*"
 redis = {extras = ["hiredis"], version = "*"}
-scikit-learn = "~=1.2"
-whitenoise = "~=6.3"
-watchdog = "~=2.2"
-whoosh="~=2.7"
-inotifyrecursive = "~=0.3"
-ocrmypdf = "~=14.0"
-tqdm = "*"
-tika-client = "*"
-channels = "~=4.0"
-channels-redis = "*"
-uvicorn = {extras = ["standard"], version = "*"}
-concurrent-log-handler = "*"
-pyzbar = "*"
-mysqlclient = "*"
-celery = {extras = ["redis"], version = "*"}
+scikit-learn = "~=1.5"
 setproctitle = "*"
-nltk = "*"
-pdf2image = "*"
-flower = "*"
-bleach = "*"
+tika-client = "*"
+tqdm = "*"
+# See https://github.com/paperless-ngx/paperless-ngx/issues/5494
+uvicorn = {extras = ["standard"], version = "==0.25.0"}
+watchdog = "~=4.0"
+whitenoise = "~=6.8"
+whoosh = "~=2.7"
 zxing-cpp = {version = "*", platform_machine = "== 'x86_64'"}
-#
-# Packages locked due to issues (try to check if these are fixed in a release every so often)
-#
-# Pin this until piwheels is building 1.9 (see https://www.piwheels.org/project/scipy/)
-scipy = "==1.8.1"
-# v4 brings in extra dependencies for features not used here
-reportlab = "==3.6.12"
-# Pin this until piwheels is building a newer version (see https://www.piwheels.org/project/cryptography/)
-cryptography = "==40.0.1"
+
 
 [dev-packages]
 # Linting
-black = "*"
 pre-commit = "*"
 ruff = "*"
-# Testing
 factory-boy = "*"
+# Testing
 pytest = "*"
 pytest-cov = "*"
 pytest-django = "*"
@@ -81,11 +74,13 @@ pytest-httpx = "*"
 pytest-env = "*"
 pytest-sugar = "*"
 pytest-xdist = "*"
-"pdfminer.six" = "*"
+pytest-mock = "*"
+pytest-rerunfailures = "*"
 imagehash = "*"
 daphne = "*"
 # Documentation
 mkdocs-material = "*"
+mkdocs-glightbox = "*"
 
 [typing-dev]
 mypy = "*"
@@ -97,12 +92,9 @@ celery-types = "*"
 django-stubs = {extras= ["compatible-mypy"], version="*"}
 types-dateparser = "*"
 types-bleach = "*"
-types-humanfriendly = "*"
 types-redis = "*"
 types-tqdm = "*"
 types-Markdown = "*"
 types-Pygments = "*"
-types-backports = "*"
 types-colorama = "*"
-types-psycopg2 = "*"
 types-setuptools = "*"

README.md

@@ -6,8 +6,11 @@
 [![demo](https://cronitor.io/badges/ve7ItY/production/W5E_B9jkelG9ZbDiNHUPQEVH3MY.svg)](https://demo.paperless-ngx.com)
 
 <p align="center">
-<img src="https://github.com/paperless-ngx/paperless-ngx/raw/main/resources/logo/web/png/Black%20logo%20-%20no%20background.png#gh-light-mode-only" width="50%" />
-<img src="https://github.com/paperless-ngx/paperless-ngx/raw/main/resources/logo/web/png/White%20logo%20-%20no%20background.png#gh-dark-mode-only" width="50%" />
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://github.com/paperless-ngx/paperless-ngx/blob/main/resources/logo/web/png/White%20logo%20-%20no%20background.png" width="50%">
+    <source media="(prefers-color-scheme: light)" srcset="https://github.com/paperless-ngx/paperless-ngx/raw/main/resources/logo/web/png/Black%20logo%20-%20no%20background.png" width="50%">
+    <img src="https://github.com/paperless-ngx/paperless-ngx/raw/main/resources/logo/web/png/Black%20logo%20-%20no%20background.png" width="50%">
+  </picture>
 </p>
 
 <!-- omit in toc -->
@@ -16,10 +19,9 @@
 
 Paperless-ngx is a document management system that transforms your physical documents into a searchable online archive so you can keep, well, _less paper_.
 
-Paperless-ngx forked from [paperless-ng](https://github.com/jonaswinkler/paperless-ng) to continue the great work and distribute responsibility of supporting and advancing the project among a team of people. [Consider joining us!](#community-support) Discussion of this transition can be found in issues
-[#1599](https://github.com/jonaswinkler/paperless-ng/issues/1599) and [#1632](https://github.com/jonaswinkler/paperless-ng/issues/1632).
+Paperless-ngx is the official successor to the original [Paperless](https://github.com/the-paperless-project/paperless) & [Paperless-ng](https://github.com/jonaswinkler/paperless-ng) projects and is designed to distribute the responsibility of advancing and supporting the project among a team of people. [Consider joining us!](#community-support)
 
-A demo is available at [demo.paperless-ngx.com](https://demo.paperless-ngx.com) using login `demo` / `demo`. _Note: demo content is reset frequently and confidential information should not be uploaded._
+Thanks to the generous folks at [DigitalOcean](https://m.do.co/c/8d70b916d462), a demo is available at [demo.paperless-ngx.com](https://demo.paperless-ngx.com) using login `demo` / `demo`. _Note: demo content is reset frequently and confidential information should not be uploaded._
 
 - [Features](#features)
 - [Getting started](#getting-started)
@@ -28,48 +30,40 @@ A demo is available at [demo.paperless-ngx.com](https://demo.paperless-ngx.com)
   - [Translation](#translation)
   - [Feature Requests](#feature-requests)
   - [Bugs](#bugs)
-- [Affiliated Projects](#affiliated-projects)
+- [Related Projects](#related-projects)
 - [Important Note](#important-note)
 
+<p align="right">This project is supported by:<br/>
+  <a href="https://m.do.co/c/8d70b916d462" style="padding-top: 4px; display: block;">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" srcset="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_white.svg" width="140px">
+      <source media="(prefers-color-scheme: light)" srcset="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_blue.svg" width="140px">
+      <img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_black_.svg" width="140px">
+    </picture>
+  </a>
+</p>
+
 # Features
 
-![Dashboard](https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/assets/screenshots/documents-smallcards.png#gh-light-mode-only)
-![Dashboard](https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/assets/screenshots/documents-smallcards-dark.png#gh-dark-mode-only)
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/assets/screenshots/documents-smallcards-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/assets/screenshots/documents-smallcards.png">
+  <img src="https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/assets/screenshots/documents-smallcards.png">
+</picture>
 
-- Organize and index your scanned documents with tags, correspondents, types, and more.
-- Performs OCR on your documents, adds selectable text to image only documents and adds tags, correspondents and document types to your documents.
-- Supports PDF documents, images, plain text files, and Office documents (Word, Excel, Powerpoint, and LibreOffice equivalents).
-  - Office document support is optional and provided by Apache Tika (see [configuration](https://docs.paperless-ngx.com/configuration/#tika))
-- Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely.
-- Single page application front end.
-  - Includes a dashboard that shows basic statistics and has document upload.
-  - Filtering by tags, correspondents, types, and more.
-  - Customizable views can be saved and displayed on the dashboard.
-- Full text search helps you find what you need.
-  - Auto completion suggests relevant words from your documents.
-  - Results are sorted by relevance to your search query.
-  - Highlighting shows you which parts of the document matched the query.
-  - Searching for similar documents ("More like this")
-- Email processing: Paperless adds documents from your email accounts.
-  - Configure multiple accounts and filters for each account.
-  - When adding documents from mail, paperless can move these mail to a new folder, mark them as read, flag them as important or delete them.
-- Machine learning powered document matching.
-  - Paperless-ngx learns from your documents and will be able to automatically assign tags, correspondents and types to documents once you've stored a few documents in paperless.
-- Optimized for multi core systems: Paperless-ngx consumes multiple documents in parallel.
-- The integrated sanity checker makes sure that your document archive is in good health.
-- [More screenshots are available in the documentation](https://docs.paperless-ngx.com/#screenshots).
+A full list of [features](https://docs.paperless-ngx.com/#features) and [screenshots](https://docs.paperless-ngx.com/#screenshots) are available in the [documentation](https://docs.paperless-ngx.com/).
 
 # Getting started
 
-The easiest way to deploy paperless is docker-compose. The files in the [`/docker/compose` directory](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose) are configured to pull the image from Github Packages.
+The easiest way to deploy paperless is `docker compose`. The files in the [`/docker/compose` directory](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose) are configured to pull the image from GitHub Packages.
 
-If you'd like to jump right in, you can configure a docker-compose environment with our install script:
+If you'd like to jump right in, you can configure a `docker compose` environment with our install script:
 
 ```bash
 bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
 ```
 
-Alternatively, you can install the dependencies and setup apache and a database server yourself. The [documentation](https://docs.paperless-ngx.com/setup/#installation) has a step by step guide on how to do it.
+More details and step-by-step guides for alternative installation methods can be found in [the documentation](https://docs.paperless-ngx.com/setup/#installation).
 
 Migrating from Paperless-ng is easy, just drop in the new docker image! See the [documentation on migrating](https://docs.paperless-ngx.com/setup/#migrating-to-paperless-ngx) for more details.
 
@@ -85,7 +79,7 @@ If you feel like contributing to the project, please do! Bug fixes, enhancements
 
 ## Community Support
 
-People interested in continuing the work on paperless-ngx are encouraged to reach out here on github and in the [Matrix Room](https://matrix.to/#/#paperless:adnidor.de). If you would like to contribute to the project on an ongoing basis there are multiple [teams](https://github.com/orgs/paperless-ngx/people) (frontend, ci/cd, etc) that could use your help so please reach out!
+People interested in continuing the work on paperless-ngx are encouraged to reach out here on github and in the [Matrix Room](https://matrix.to/#/#paperless:matrix.org). If you would like to contribute to the project on an ongoing basis there are multiple [teams](https://github.com/orgs/paperless-ngx/people) (frontend, ci/cd, etc) that could use your help so please reach out!
 
 ## Translation
 
@@ -99,9 +93,9 @@ Feature requests can be submitted via [GitHub Discussions](https://github.com/pa
 
 For bugs please [open an issue](https://github.com/paperless-ngx/paperless-ngx/issues) or [start a discussion](https://github.com/paperless-ngx/paperless-ngx/discussions) if you have questions.
 
-# Affiliated Projects
+# Related Projects
 
-Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Affiliated-Projects) for a user-maintained list of affiliated projects and software that is compatible with Paperless-ngx.
+Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects) for a user-maintained list of related projects and software that is compatible with Paperless-ngx.
 
 # Important Note
 

SECURITY.md

@@ -0,0 +1,9 @@
+# Security Policy
+
+## Reporting a Vulnerability
+
+The Paperless-ngx team and community take security bugs seriously. We appreciate your efforts to responsibly disclose your findings, and will make every effort to acknowledge your contributions.
+
+To report a security issue, please use the GitHub Security Advisory ["Report a Vulnerability"](https://github.com/paperless-ngx/paperless-ngx/security/advisories/new) tab.
+
+The team will send a response indicating the next steps in handling your report. After the initial reply to your report, the security team will keep you informed of the progress towards a fix and full announcement, and may ask for additional information or guidance.

crowdin.yml

@@ -1,8 +1,6 @@
-commit_message: '[ci skip]'
-pull_request_labels: [
-  "skip-changelog",
-  "translation"
-]
+project_id_env: CROWDIN_PROJECT_ID
+api_token_env: CROWDIN_PERSONAL_TOKEN
+preserve_hierarchy: true
 files:
   - source: /src/locale/en_US/LC_MESSAGES/django.po
     translation: /src/locale/%locale_with_underscore%/LC_MESSAGES/django.po

docker/compose/docker-compose.ci-test.yml

@@ -1,12 +1,11 @@
-# docker-compose file for running paperless testing with actual gotenberg
+# Docker Compose file for running paperless testing with actual gotenberg
 # and Tika containers for a more end to end test of the Tika related functionality
-# Can be used locally or by the CI to start the nessecary containers with the
+# Can be used locally or by the CI to start the necessary containers with the
 # correct networking for the tests
 
-version: "3.7"
 services:
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:8.7
     hostname: gotenberg
     container_name: gotenberg
     network_mode: host
@@ -17,8 +16,10 @@ services:
       - "gotenberg"
       - "--chromium-disable-javascript=true"
       - "--chromium-allow-list=file:///tmp/.*"
+      - "--log-level=warn"
+      - "--log-format=text"
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     hostname: tika
     container_name: tika
     network_mode: host

docker/compose/docker-compose.mariadb-tika.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the Docker Hub.
+# docker compose file for running paperless from the Docker Hub.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 #
@@ -10,7 +10,7 @@
 #   as this file and mounted to the correct folders inside the container.
 # - Paperless listens on port 8000.
 #
-# In addition to that, this docker-compose file adds the following optional
+# In addition to that, this Docker Compose file adds the following optional
 # configurations:
 #
 # - Instead of SQLite (default), MariaDB is used as the database server.
@@ -23,14 +23,13 @@
 #
 # - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
 #   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
+# - Run 'docker compose pull'.
+# - Run 'docker compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker compose up -d'.
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -39,7 +38,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/mariadb:10
+    image: docker.io/library/mariadb:11
     restart: unless-stopped
     volumes:
       - dbdata:/var/lib/mysql
@@ -60,11 +59,6 @@ services:
       - tika
     ports:
       - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media
@@ -83,7 +77,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:8.7
     restart: unless-stopped
     # The gotenberg chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even javascript.
@@ -93,7 +87,7 @@ services:
       - "--chromium-allow-list=file:///tmp/.*"
 
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.mariadb.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the Docker Hub.
+# Docker Compose file for running paperless from the Docker Hub.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 #
@@ -10,7 +10,7 @@
 #   as this file and mounted to the correct folders inside the container.
 # - Paperless listens on port 8000.
 #
-# In addition to that, this docker-compose file adds the following optional
+# In addition to that, this Docker Compose file adds the following optional
 # configurations:
 #
 # - Instead of SQLite (default), MariaDB is used as the database server.
@@ -19,14 +19,13 @@
 #
 # - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
 #   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
+# - Run 'docker compose pull'.
+# - Run 'docker compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker compose up -d'.
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -35,7 +34,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/mariadb:10
+    image: docker.io/library/mariadb:11
     restart: unless-stopped
     volumes:
       - dbdata:/var/lib/mysql
@@ -54,11 +53,6 @@ services:
       - broker
     ports:
       - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media
@@ -73,7 +67,6 @@ services:
       PAPERLESS_DBPASS: paperless # only needed if non-default password
       PAPERLESS_DBPORT: 3306
 
-
 volumes:
   data:
   media:

docker/compose/docker-compose.portainer.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the Docker Hub.
+# Docker Compose file for running paperless from the Docker Hub.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 #
@@ -10,7 +10,7 @@
 #   as this file and mounted to the correct folders inside the container.
 # - Paperless listens on port 8010.
 #
-# In addition to that, this docker-compose file adds the following optional
+# In addition to that, this Docker Compose file adds the following optional
 # configurations:
 #
 # - Instead of SQLite (default), PostgreSQL is used as the database server.
@@ -18,7 +18,7 @@
 # To install and update paperless with this file, do the following:
 #
 # - Open portainer Stacks list and click 'Add stack'
-# - Paste the contents of this file and assign a name, e.g. 'Paperless'
+# - Paste the contents of this file and assign a name, e.g. 'paperless'
 # - Click 'Deploy the stack' and wait for it to be deployed
 # - Open the list of containers, select paperless_webserver_1
 # - Click 'Console' and then 'Connect' to open the command line inside the container
@@ -28,7 +28,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -37,7 +36,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/postgres:13
+    image: docker.io/library/postgres:16
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -54,11 +53,6 @@ services:
       - broker
     ports:
       - "8010:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media

docker/compose/docker-compose.postgres-tika.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the docker container registry.
+# Docker Compose file for running paperless from the docker container registry.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 #
@@ -10,7 +10,7 @@
 #   as this file and mounted to the correct folders inside the container.
 # - Paperless listens on port 8000.
 #
-# In addition to that, this docker-compose file adds the following optional
+# In addition to that, this Docker Compose file adds the following optional
 # configurations:
 #
 # - Instead of SQLite (default), PostgreSQL is used as the database server.
@@ -23,14 +23,13 @@
 #
 # - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
 #   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
+# - Run 'docker compose pull'.
+# - Run 'docker compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker compose up -d'.
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -39,7 +38,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/postgres:13
+    image: docker.io/library/postgres:16
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -58,11 +57,6 @@ services:
       - tika
     ports:
       - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media
@@ -77,7 +71,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:8.7
     restart: unless-stopped
 
     # The gotenberg chromium route is used to convert .eml files. We do not
@@ -88,7 +82,7 @@ services:
       - "--chromium-allow-list=file:///tmp/.*"
 
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.postgres.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the Docker Hub.
+# Docker Compose file for running paperless from the Docker Hub.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 #
@@ -10,7 +10,7 @@
 #   as this file and mounted to the correct folders inside the container.
 # - Paperless listens on port 8000.
 #
-# In addition to that, this docker-compose file adds the following optional
+# In addition to that, this Docker Compose file adds the following optional
 # configurations:
 #
 # - Instead of SQLite (default), PostgreSQL is used as the database server.
@@ -19,14 +19,13 @@
 #
 # - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
 #   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
+# - Run 'docker compose pull'.
+# - Run 'docker compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker compose up -d'.
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -35,7 +34,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/postgres:13
+    image: docker.io/library/postgres:16
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -52,11 +51,6 @@ services:
       - broker
     ports:
       - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media
@@ -67,7 +61,6 @@ services:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_DBHOST: db
 
-
 volumes:
   data:
   media:

docker/compose/docker-compose.sqlite-tika.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the docker container registry.
+# Docker Compose file for running paperless from the docker container registry.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 # All compose files of paperless configure paperless in the following way:
@@ -11,7 +11,7 @@
 #
 # SQLite is used as the database. The SQLite file is stored in the data volume.
 #
-# In addition to that, this docker-compose file adds the following optional
+# In addition to that, this Docker Compose file adds the following optional
 # configurations:
 #
 # - Apache Tika and Gotenberg servers are started with paperless and paperless
@@ -23,14 +23,13 @@
 #
 # - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
 #   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
+# - Run 'docker compose pull'.
+# - Run 'docker compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker compose up -d'.
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -47,11 +46,6 @@ services:
       - tika
     ports:
       - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media
@@ -65,7 +59,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:8.7
     restart: unless-stopped
 
     # The gotenberg chromium route is used to convert .eml files. We do not
@@ -76,7 +70,7 @@ services:
       - "--chromium-allow-list=file:///tmp/.*"
 
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.sqlite.yml

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the Docker Hub.
+# Docker Compose file for running paperless from the Docker Hub.
 # This file contains everything paperless needs to run.
 # Paperless supports amd64, arm and arm64 hardware.
 #
@@ -16,14 +16,13 @@
 #
 # - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
 #   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
+# - Run 'docker compose pull'.
+# - Run 'docker compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker compose up -d'.
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -38,11 +37,6 @@ services:
       - broker
     ports:
       - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
     volumes:
       - data:/usr/src/paperless/data
       - media:/usr/src/paperless/media
@@ -52,7 +46,6 @@ services:
     environment:
       PAPERLESS_REDIS: redis://broker:6379
 
-
 volumes:
   data:
   media:

docker/docker-entrypoint.sh

@@ -10,8 +10,8 @@ map_uidgid() {
 	local -r usermap_new_gid=${USERMAP_GID:-${usermap_original_gid:-$usermap_new_uid}}
 	if [[ ${usermap_new_uid} != "${usermap_original_uid}" || ${usermap_new_gid} != "${usermap_original_gid}" ]]; then
 		echo "Mapping UID and GID for paperless:paperless to $usermap_new_uid:$usermap_new_gid"
-		usermod -o -u "${usermap_new_uid}" paperless
-		groupmod -o -g "${usermap_new_gid}" paperless
+		usermod --non-unique --uid "${usermap_new_uid}" paperless
+		groupmod --non-unique --gid "${usermap_new_gid}" paperless
 	fi
 }
 
@@ -42,7 +42,7 @@ custom_container_init() {
 		fi
 
 		# Make sure custom init directory has files in it
-		if [ -n "$(/bin/ls -A "${custom_script_dir}" 2>/dev/null)" ]; then
+		if [ -n "$(/bin/ls --almost-all "${custom_script_dir}" 2>/dev/null)" ]; then
 			echo "[custom-init] files found in ${custom_script_dir} executing"
 			# Loop over files in the directory
 			for SCRIPT in "${custom_script_dir}"/*; do
@@ -86,23 +86,23 @@ initialize() {
 		"${CONSUME_DIR}"; do
 		if [[ ! -d "${dir}" ]]; then
 			echo "Creating directory ${dir}"
-			mkdir "${dir}"
+			mkdir --parents --verbose "${dir}"
 		fi
 	done
 
-	local -r tmp_dir="/tmp/paperless"
-	echo "Creating directory ${tmp_dir}"
-	mkdir -p "${tmp_dir}"
+	local -r tmp_dir="${PAPERLESS_SCRATCH_DIR:=/tmp/paperless}"
+	echo "Creating directory scratch directory ${tmp_dir}"
+	mkdir --parents --verbose "${tmp_dir}"
 
 	set +e
 	echo "Adjusting permissions of paperless files. This may take a while."
-	chown -R paperless:paperless ${tmp_dir}
+	chown -R paperless:paperless "${tmp_dir}"
 	for dir in \
 		"${export_dir}" \
 		"${DATA_DIR}" \
 		"${MEDIA_ROOT_DIR}" \
 		"${CONSUME_DIR}"; do
-		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown paperless:paperless {} +
+		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown --changes paperless:paperless {} +
 	done
 	set -e
 
@@ -122,33 +122,44 @@ install_languages() {
 	if [ ${#langs[@]} -eq 0 ]; then
 		return
 	fi
-	apt-get update
 
+	# Build list of packages to install
+	to_install=()
 	for lang in "${langs[@]}"; do
 		pkg="tesseract-ocr-$lang"
 
-		if dpkg -s "$pkg" &>/dev/null; then
+		if dpkg --status "$pkg" &>/dev/null; then
 			echo "Package $pkg already installed!"
 			continue
-		fi
-
-		if ! apt-cache show "$pkg" &>/dev/null; then
-			echo "Package $pkg not found! :("
-			continue
-		fi
-
-		echo "Installing package $pkg..."
-		if ! apt-get -y install "$pkg" &>/dev/null; then
-			echo "Could not install $pkg"
-			exit 1
+		else
+			to_install+=("$pkg")
 		fi
 	done
+
+	# Use apt only when we install packages
+	if [ ${#to_install[@]} -gt 0 ]; then
+		apt-get update
+
+		for pkg in "${to_install[@]}"; do
+
+			if ! apt-cache show "$pkg" &>/dev/null; then
+				echo "Skipped $pkg: Package not found! :("
+				continue
+			fi
+
+			echo "Installing package $pkg..."
+			if ! apt-get --assume-yes install "$pkg" &>/dev/null; then
+				echo "Could not install $pkg"
+				exit 1
+			fi
+		done
+	fi
 }
 
 echo "Paperless-ngx docker container starting..."
 
 gosu_cmd=(gosu paperless)
-if [ "$(id -u)" == "$(id -u paperless)" ]; then
+if [ "$(id --user)" == "$(id --user paperless)" ]; then
 	gosu_cmd=()
 fi
 

docker/docker-prepare.sh

@@ -13,7 +13,7 @@ wait_for_postgres() {
 
 	# Disable warning, host and port can't have spaces
 	# shellcheck disable=SC2086
-	while [ ! "$(pg_isready -h ${host} -p ${port})" ]; do
+	while [ ! "$(pg_isready --host ${host} --port ${port})" ]; do
 
 		if [ $attempt_num -eq $max_attempts ]; then
 			echo "Unable to connect to database."
@@ -25,6 +25,7 @@ wait_for_postgres() {
 		attempt_num=$(("$attempt_num" + 1))
 		sleep 5
 	done
+	echo "Connected to PostgreSQL"
 }
 
 wait_for_mariadb() {
@@ -51,6 +52,7 @@ wait_for_mariadb() {
 		attempt_num=$(("$attempt_num" + 1))
 		sleep 5
 	done
+	echo "Connected to MariaDB"
 }
 
 wait_for_redis() {
@@ -80,7 +82,7 @@ django_checks() {
 
 search_index() {
 
-	local -r index_version=6
+	local -r index_version=9
 	local -r index_version_file=${DATA_DIR}/.index_version
 
 	if [[ (! -f "${index_version_file}") || $(<"${index_version_file}") != "$index_version" ]]; then

docker/env-from-file.sh

@@ -16,7 +16,7 @@ do
 	# Check if it starts with "PAPERLESS_" and ends in "_FILE"
 	if [[ ${env_name} == PAPERLESS_*_FILE ]]; then
 		# This should have been named different..
-		if [[ ${env_name} == "PAPERLESS_OCR_SKIP_ARCHIVE_FILE" ]]; then
+		if [[ ${env_name} == "PAPERLESS_OCR_SKIP_ARCHIVE_FILE" || ${env_name} == "PAPERLESS_MODEL_FILE" ]]; then
 			continue
 		fi
 		# Extract the value of the environment

docker/install_management_commands.sh

@@ -13,7 +13,9 @@ for command in decrypt_documents \
 	document_retagger \
 	document_thumbnails \
 	document_sanity_checker \
-	manage_superuser;
+	document_fuzzy_match \
+	manage_superuser \
+	convert_mariadb_uuid;
 do
 	echo "installing $command..."
 	sed "s/management_command/$command/g" management_script.sh > /usr/local/bin/$command

docker/paperless_cmd.sh

@@ -1,14 +1,15 @@
 #!/usr/bin/env bash
 
+SUPERVISORD_WORKING_DIR="${PAPERLESS_SUPERVISORD_WORKING_DIR:-$PWD}"
 rootless_args=()
 if [ "$(id -u)" == "$(id -u paperless)" ]; then
 	rootless_args=(
 		--user
 		paperless
 		--logfile
-		supervisord.log
+		"${SUPERVISORD_WORKING_DIR}/supervisord.log"
 		--pidfile
-		supervisord.pid
+		"${SUPERVISORD_WORKING_DIR}/supervisord.pid"
 	)
 fi
 

docker/supervisord.conf

@@ -15,6 +15,7 @@ stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
+environment = HOME="/usr/src/paperless",USER="paperless"
 
 [program:consumer]
 command=python3 manage.py document_consumer
@@ -25,6 +26,7 @@ stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
+environment = HOME="/usr/src/paperless",USER="paperless"
 
 [program:celery]
 
@@ -37,6 +39,7 @@ stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
+environment = HOME="/usr/src/paperless",USER="paperless"
 
 [program:celery-beat]
 
@@ -48,6 +51,7 @@ stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
+environment = HOME="/usr/src/paperless",USER="paperless"
 
 [program:celery-flower]
 command = /usr/local/bin/flower-conditional.sh
@@ -58,3 +62,4 @@ stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
+environment = HOME="/usr/src/paperless",USER="paperless"

docker/wait-for-redis.py

@@ -4,6 +4,7 @@ Simple script which attempts to ping the Redis broker as set in the environment
 a certain number of times, waiting a little bit in between
 
 """
+
 import os
 import sys
 import time

docs/administration.md

@@ -5,17 +5,21 @@
 Multiple options exist for making backups of your paperless instance,
 depending on how you installed paperless.
 
-Before making backups, make sure that paperless is not running.
+Before making a backup, it's probably best to make sure that paperless is not actively
+consuming documents at that time.
 
 Options available to any installation of paperless:
 
-- Use the [document exporter](#exporter). The document exporter exports all your documents,
-  thumbnails and metadata to a specific folder. You may import your
-  documents into a fresh instance of paperless again or store your
-  documents in another DMS with this export.
-- The document exporter is also able to update an already existing
-  export. Therefore, incremental backups with `rsync` are entirely
-  possible.
+-   Use the [document exporter](#exporter). The document exporter exports all your documents,
+    thumbnails, metadata, and database contents to a specific folder. You may import your
+    documents and settings into a fresh instance of paperless again or store your
+    documents in another DMS with this export.
+
+    The document exporter is also able to update an already existing
+    export. Therefore, incremental backups with `rsync` are entirely
+    possible.
+
+    The exporter does not include API tokens and they will need to be re-generated after importing.
 
 !!! caution
 
@@ -25,31 +29,37 @@ Options available to any installation of paperless:
 
 Options available to docker installations:
 
-- Backup the docker volumes. These usually reside within
-  `/var/lib/docker/volumes` on the host and you need to be root in
-  order to access them.
+-   Backup the docker volumes. These usually reside within
+    `/var/lib/docker/volumes` on the host and you need to be root in
+    order to access them.
 
-  Paperless uses 4 volumes:
+    Paperless uses 4 volumes:
 
-  - `paperless_media`: This is where your documents are stored.
-  - `paperless_data`: This is where auxillary data is stored. This
-    folder also contains the SQLite database, if you use it.
-  - `paperless_pgdata`: Exists only if you use PostgreSQL and
-    contains the database.
-  - `paperless_dbdata`: Exists only if you use MariaDB and contains
-    the database.
+    -   `paperless_media`: This is where your documents are stored.
+    -   `paperless_data`: This is where auxiliary data is stored. This
+        folder also contains the SQLite database, if you use it.
+    -   `paperless_pgdata`: Exists only if you use PostgreSQL and
+        contains the database.
+    -   `paperless_dbdata`: Exists only if you use MariaDB and contains
+        the database.
 
 Options available to bare-metal and non-docker installations:
 
-- Backup the entire paperless folder. This ensures that if your
-  paperless instance crashes at some point or your disk fails, you can
-  simply copy the folder back into place and it works.
+-   Backup the entire paperless folder. This ensures that if your
+    paperless instance crashes at some point or your disk fails, you can
+    simply copy the folder back into place and it works.
 
-  When using PostgreSQL or MariaDB, you'll also have to backup the
-  database.
+    When using PostgreSQL or MariaDB, you'll also have to backup the
+    database.
 
 ### Restoring {#migrating-restoring}
 
+If you've backed-up Paperless-ngx using the [document exporter](#exporter),
+restoring can simply be done with the [document importer](#importer).
+
+Of course, other backup strategies require restoring any volumes, folders and database
+copies you created in the steps above.
+
 ## Updating Paperless {#updating}
 
 ### Docker Route {#docker-updating}
@@ -59,34 +69,34 @@ you installed paperless-ngx in the first place. The releases are
 available at the [release
 page](https://github.com/paperless-ngx/paperless-ngx/releases).
 
-First of all, ensure that paperless is stopped.
+First of all, make sure no active processes (like consumption) are running, then [make a backup](#backup).
+
+After that, ensure that paperless is stopped:
 
 ```shell-session
 $ cd /path/to/paperless
-$ docker-compose down
+$ docker compose down
 ```
 
-After that, [make a backup](#backup).
+1.  If you pull the image from the docker hub, all you need to do is:
 
-1. If you pull the image from the docker hub, all you need to do is:
+    ```shell-session
+    $ docker compose pull
+    $ docker compose up
+    ```
 
-   ```shell-session
-   $ docker-compose pull
-   $ docker-compose up
-   ```
+    The Docker Compose files refer to the `latest` version, which is
+    always the latest stable release.
 
-   The docker-compose files refer to the `latest` version, which is
-   always the latest stable release.
+1.  If you built the image yourself, do the following:
 
-2. If you built the image yourself, do the following:
+    ```shell-session
+    $ git pull
+    $ docker compose build
+    $ docker compose up
+    ```
 
-   ```shell-session
-   $ git pull
-   $ docker-compose build
-   $ docker-compose up
-   ```
-
-Running `docker-compose up` will also apply any new database migrations.
+Running `docker compose up` will also apply any new database migrations.
 If you see everything working, press CTRL+C once to gracefully stop
 paperless. Then you can start paperless-ngx with `-d` to have it run in
 the background.
@@ -94,7 +104,7 @@ the background.
 !!! note
 
     In version 0.9.14, the update process was changed. In 0.9.13 and
-    earlier, the docker-compose files specified exact versions and pull
+    earlier, the Docker Compose files specified exact versions and pull
     won't automatically update to newer versions. In order to enable
     updates as described above, either get the new `docker-compose.yml`
     file from
@@ -139,7 +149,7 @@ following:
 1.  Update dependencies. New paperless version may require additional
     dependencies. The dependencies required are listed in the section
     about
-    [bare metal installations](/setup#bare_metal).
+    [bare metal installations](setup.md#bare_metal).
 
 2.  Update python requirements. Keep in mind to activate your virtual
     environment before that, if you use one.
@@ -167,34 +177,22 @@ following:
     This might not actually do anything. Not every new paperless version
     comes with new database migrations.
 
-## Downgrading Paperless {#downgrade-paperless}
+### Database Upgrades
 
-Downgrades are possible. However, some updates also contain database
-migrations (these change the layout of the database and may move data).
-In order to move back from a version that applied database migrations,
-you'll have to revert the database migration _before_ downgrading, and
-then downgrade paperless.
+In general, paperless does not require a specific version of PostgreSQL or MariaDB and it is
+safe to update them to newer versions. However, you should always take a backup and follow
+the instructions from your database's documentation for how to upgrade between major versions.
 
-This table lists the compatible versions for each database migration
-number.
+For PostgreSQL, refer to [Upgrading a PostgreSQL Cluster](https://www.postgresql.org/docs/current/upgrading.html).
 
-| Migration number | Version range   |
-| ---------------- | --------------- |
-| 1011             | 1.0.0           |
-| 1012             | 1.1.0 - 1.2.1   |
-| 1014             | 1.3.0 - 1.3.1   |
-| 1016             | 1.3.2 - current |
+For MariaDB, refer to [Upgrading MariaDB](https://mariadb.com/kb/en/upgrading/)
 
-Execute the following management command to migrate your database:
+You may also use the exporter and importer with the `--data-only` flag, after creating a new database with the updated version of PostgreSQL or MariaDB.
 
-```shell-session
-$ python3 manage.py migrate documents <migration number>
-```
+!!! warning
 
-!!! note
-
-    Some migrations cannot be undone. The command will issue errors if that
-    happens.
+    You should not change any settings, especially paths, when doing this or there is a
+    risk of data loss
 
 ## Management utilities {#management-commands}
 
@@ -202,11 +200,11 @@ Paperless comes with some management commands that perform various
 maintenance tasks on your paperless instance. You can invoke these
 commands in the following way:
 
-With docker-compose, while paperless is running:
+With Docker Compose, while paperless is running:
 
 ```shell-session
 $ cd /path/to/paperless
-$ docker-compose exec webserver <command> <arguments>
+$ docker compose exec webserver <command> <arguments>
 ```
 
 With docker, while paperless is running:
@@ -229,26 +227,31 @@ with the argument `--help`.
 
 ### Document exporter {#exporter}
 
-The document exporter exports all your data from paperless into a folder
-for backup or migration to another DMS.
+The document exporter exports all your data (including your settings
+and database contents) from paperless into a folder for backup or
+migration to another DMS.
 
 If you use the document exporter within a cronjob to backup your data
 you might use the `-T` flag behind exec to suppress "The input device
 is not a TTY" errors. For example:
-`docker-compose exec -T webserver document_exporter ../export`
+`docker compose exec -T webserver document_exporter ../export`
 
 ```
 document_exporter target [-c] [-d] [-f] [-na] [-nt] [-p] [-sm] [-z]
 
 optional arguments:
--c, --compare-checksums
--d, --delete
--f, --use-filename-format
+-c,  --compare-checksums
+-d,  --delete
+-f,  --use-filename-format
 -na, --no-archive
 -nt, --no-thumbnail
--p, --use-folder-prefix
+-p,  --use-folder-prefix
 -sm, --split-manifest
--z  --zip
+-z,  --zip
+-zn, --zip-name
+--data-only
+--no-progress-bar
+--passphrase
 ```
 
 `target` is a folder to which the data gets written. This includes
@@ -276,7 +279,7 @@ other files.
 
 The filenames generated by this command follow the format
 `[date created] [correspondent] [title].[extension]`. If you want
-paperless to use `PAPERLESS_FILENAME_FORMAT` for exported filenames
+paperless to use [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) for exported filenames
 instead, specify `-f` or `--use-filename-format`.
 
 If `-na` or `--no-archive` is provided, no archive files will be exported,
@@ -304,7 +307,18 @@ manifest.json will still contain application wide information (e.g. tags, corres
 documenttype, etc)
 
 If `-z` or `--zip` is provided, the export will be a zip file
-in the target directory, named according to the current date.
+in the target directory, named according to the current local date or the
+value set in `-zn` or `--zip-name`.
+
+If `--data-only` is provided, only the database will be exported. This option is intended
+to facilitate database upgrades without needing to clean documents and thumbnails from the media directory.
+
+If `--no-progress-bar` is provided, the progress bar will be hidden, rendering the
+exporter quiet. This option is useful for scripting scenarios, such as when using the
+exporter with `crontab`.
+
+If `--passphrase` is provided, it will be used to encrypt certain fields in the export. This value
+must be provided to import. If this value is lost, the export cannot be imported.
 
 !!! warning
 
@@ -320,19 +334,34 @@ exporter](#exporter) and imports it into paperless.
 The importer works just like the exporter. You point it at a directory,
 and the script does the rest of the work:
 
-```
+```shell
 document_importer source
 ```
 
+| Option              | Required | Default | Description                                                               |
+| ------------------- | -------- | ------- | ------------------------------------------------------------------------- |
+| source              | Yes      | N/A     | The directory containing an export                                        |
+| `--no-progress-bar` | No       | False   | If provided, the progress bar will be hidden                              |
+| `--data-only`       | No       | False   | If provided, only import data, do not import document files or thumbnails |
+| `--passphrase`      | No       | N/A     | If your export was encrypted with a passphrase, must be provided          |
+
 When you use the provided docker compose script, put the export inside
 the `export` folder in your paperless source directory. Specify
 `../export` as the `source`.
 
+Note that .zip files (as can be generated from the exporter) are not supported. You must unzip them into
+the target directory first.
+
 !!! note
 
     Importing from a previous version of Paperless may work, but for best
     results it is suggested to match the versions.
 
+!!! warning
+
+    The importer should be run against a completely empty installation (database and directories) of Paperless-ngx.
+    If using a data only import, only the database must be empty.
+
 ### Document retagger {#retagger}
 
 Say you've imported a few hundred documents and now want to introduce a
@@ -341,7 +370,7 @@ currently-imported docs. This problem is common enough that there are
 tools for it.
 
 ```
-document_retagger [-h] [-c] [-T] [-t] [-i] [--use-first] [-f]
+document_retagger [-h] [-c] [-T] [-t] [-i] [--id-range] [--use-first] [-f]
 
 optional arguments:
 -c, --correspondent
@@ -349,6 +378,7 @@ optional arguments:
 -t, --document_type
 -s, --storage_path
 -i, --inbox-only
+--id-range
 --use-first
 -f, --overwrite
 ```
@@ -365,6 +395,11 @@ Specify `-i` to have the document retagger work on documents tagged with
 inbox tags only. This is useful when you don't want to mess with your
 already processed documents.
 
+Specify `--id-range 1 100` to have the document retagger work only on a
+specific range of document id´s. This can be useful if you have a lot of
+documents and want to test the matching rules only on a subset of
+documents.
+
 When multiple document types or correspondents match a single document,
 the retagger won't assign these to the document. Specify `--use-first`
 to override this behavior and just use the first correspondent or type
@@ -381,7 +416,7 @@ that don't match a document anymore get removed as well.
 ### Managing the Automatic matching algorithm
 
 The _Auto_ matching algorithm requires a trained neural network to work.
-This network needs to be updated whenever somethings in your data
+This network needs to be updated whenever something in your data
 changes. The docker image takes care of that automatically with the task
 scheduler. You can manually renew the classifier by invoking the
 following management command:
@@ -396,6 +431,9 @@ This command takes no arguments.
 
 Use this command to re-create document thumbnails. Optionally include the ` --document {id}` option to generate thumbnails for a specific document only.
 
+You may also specify `--processes` to control the number of processes used to generate new thumbnails. The default is to utilize
+a quarter of the available processors.
+
 ```
 document_thumbnails
 ```
@@ -423,7 +461,7 @@ task scheduler.
 ### Managing filenames {#renamer}
 
 If you use paperless' feature to
-[assign custom filenames to your documents](/advanced_usage#file-name-handling), you can use this command to move all your files after
+[assign custom filenames to your documents](advanced_usage.md#file-name-handling), you can use this command to move all your files after
 changing the naming scheme.
 
 !!! warning
@@ -448,19 +486,19 @@ collection for issues.
 
 The issues detected by the sanity checker are as follows:
 
-- Missing original files.
-- Missing archive files.
-- Inaccessible original files due to improper permissions.
-- Inaccessible archive files due to improper permissions.
-- Corrupted original documents by comparing their checksum against
-  what is stored in the database.
-- Corrupted archive documents by comparing their checksum against what
-  is stored in the database.
-- Missing thumbnails.
-- Inaccessible thumbnails due to improper permissions.
-- Documents without any content (warning).
-- Orphaned files in the media directory (warning). These are files
-  that are not referenced by any document im paperless.
+-   Missing original files.
+-   Missing archive files.
+-   Inaccessible original files due to improper permissions.
+-   Inaccessible archive files due to improper permissions.
+-   Corrupted original documents by comparing their checksum against
+    what is stored in the database.
+-   Corrupted archive documents by comparing their checksum against what
+    is stored in the database.
+-   Missing thumbnails.
+-   Inaccessible thumbnails due to improper permissions.
+-   Documents without any content (warning).
+-   Orphaned files in the media directory (warning). These are files
+    that are not referenced by any document in paperless.
 
 ```
 document_sanity_checker
@@ -529,7 +567,7 @@ Documents can be stored in Paperless using GnuPG encryption.
 
 !!! warning
 
-    Encryption is deprecated since [paperless-ng 0.9](/changelog#paperless-ng-090) and doesn't really
+    Encryption is deprecated since [paperless-ng 0.9](changelog.md#paperless-ng-090) and doesn't really
     provide any additional security, since you have to store the passphrase
     in a configuration file on the same system as the encrypted documents
     for paperless to work. Furthermore, the entire text content of the
@@ -556,3 +594,31 @@ it here)
 ```
 decrypt_documents [--passphrase SECR3TP4SSPHRA$E]
 ```
+
+### Detecting duplicates {#fuzzy_duplicate}
+
+Paperless already catches and prevents upload of exactly matching documents,
+however a new scan of an existing document may not produce an exact bit for bit
+duplicate. But the content should be exact or close, allowing detection.
+
+This tool does a fuzzy match over document content, looking for
+those which look close according to a given ratio.
+
+At this time, other metadata (such as correspondent or type) is not
+taken into account by the detection.
+
+```
+document_fuzzy_match [--ratio] [--processes N]
+```
+
+| Option      | Required | Default             | Description                                                                                                                    |
+| ----------- | -------- | ------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
+| --ratio     | No       | 85.0                | a number between 0 and 100, setting how similar a document must be for it to be reported. Higher numbers mean more similarity. |
+| --processes | No       | 1/4 of system cores | Number of processes to use for matching. Setting 1 disables multiple processes                                                 |
+| --delete    | No       | False               | If provided, one document of a matched pair above the ratio will be deleted.                                                   |
+
+!!! warning
+
+    If providing the `--delete` option, it is highly recommended to have a backup.
+    While every effort has been taken to ensure proper operation, there is always the
+    chance of deletion of a file you want to keep.

docs/advanced_usage.md

@@ -1,6 +1,6 @@
 # Advanced Topics
 
-Paperless offers a couple features that automate certain tasks and make
+Paperless offers a couple of features that automate certain tasks and make
 your life easier.
 
 ## Matching tags, correspondents, document types, and storage paths {#matching}
@@ -25,19 +25,20 @@ documents.
 
 The following algorithms are available:
 
-- **None:** No matching will be performed.
-- **Any:** Looks for any occurrence of any word provided in match in
-  the PDF. If you define the match as `Bank1 Bank2`, it will match
-  documents containing either of these terms.
-- **All:** Requires that every word provided appears in the PDF,
-  albeit not in the order provided.
-- **Exact:** Matches only if the match appears exactly as provided
-  (i.e. preserve ordering) in the PDF.
-- **Regular expression:** Parses the match as a regular expression and
-  tries to find a match within the document.
-- **Fuzzy match:** I don't know. Look at the source.
-- **Auto:** Tries to automatically match new documents. This does not
-  require you to set a match. See the notes below.
+-   **None:** No matching will be performed.
+-   **Any:** Looks for any occurrence of any word provided in match in
+    the PDF. If you define the match as `Bank1 Bank2`, it will match
+    documents containing either of these terms.
+-   **All:** Requires that every word provided appears in the PDF,
+    albeit not in the order provided.
+-   **Exact:** Matches only if the match appears exactly as provided
+    (i.e. preserve ordering) in the PDF.
+-   **Regular expression:** Parses the match as a regular expression and
+    tries to find a match within the document.
+-   **Fuzzy match:** Uses a partial matching based on locating the tag text
+    inside the document, using a [partial ratio](https://rapidfuzz.github.io/RapidFuzz/Usage/fuzz.html#partial-ratio)
+-   **Auto:** Tries to automatically match new documents. This does not
+    require you to set a match. See the [notes below](#automatic-matching).
 
 When using the _any_ or _all_ matching algorithms, you can search for
 terms that consist of multiple words by enclosing them in double quotes.
@@ -68,45 +69,45 @@ Paperless tries to hide much of the involved complexity with this
 approach. However, there are a couple caveats you need to keep in mind
 when using this feature:
 
-- Changes to your documents are not immediately reflected by the
-  matching algorithm. The neural network needs to be _trained_ on your
-  documents after changes. Paperless periodically (default: once each
-  hour) checks for changes and does this automatically for you.
-- The Auto matching algorithm only takes documents into account which
-  are NOT placed in your inbox (i.e. have any inbox tags assigned to
-  them). This ensures that the neural network only learns from
-  documents which you have correctly tagged before.
-- The matching algorithm can only work if there is a correlation
-  between the tag, correspondent, document type, or storage path and
-  the document itself. Your bank statements usually contain your bank
-  account number and the name of the bank, so this works reasonably
-  well, However, tags such as "TODO" cannot be automatically
-  assigned.
-- The matching algorithm needs a reasonable number of documents to
-  identify when to assign tags, correspondents, storage paths, and
-  types. If one out of a thousand documents has the correspondent
-  "Very obscure web shop I bought something five years ago", it will
-  probably not assign this correspondent automatically if you buy
-  something from them again. The more documents, the better.
-- Paperless also needs a reasonable amount of negative examples to
-  decide when not to assign a certain tag, correspondent, document
-  type, or storage path. This will usually be the case as you start
-  filling up paperless with documents. Example: If all your documents
-  are either from "Webshop" and "Bank", paperless will assign one
-  of these correspondents to ANY new document, if both are set to
-  automatic matching.
+-   Changes to your documents are not immediately reflected by the
+    matching algorithm. The neural network needs to be _trained_ on your
+    documents after changes. Paperless periodically (default: once each
+    hour) checks for changes and does this automatically for you.
+-   The Auto matching algorithm only takes documents into account which
+    are NOT placed in your inbox (i.e. have any inbox tags assigned to
+    them). This ensures that the neural network only learns from
+    documents which you have correctly tagged before.
+-   The matching algorithm can only work if there is a correlation
+    between the tag, correspondent, document type, or storage path and
+    the document itself. Your bank statements usually contain your bank
+    account number and the name of the bank, so this works reasonably
+    well, However, tags such as "TODO" cannot be automatically
+    assigned.
+-   The matching algorithm needs a reasonable number of documents to
+    identify when to assign tags, correspondents, storage paths, and
+    types. If one out of a thousand documents has the correspondent
+    "Very obscure web shop I bought something five years ago", it will
+    probably not assign this correspondent automatically if you buy
+    something from them again. The more documents, the better.
+-   Paperless also needs a reasonable amount of negative examples to
+    decide when not to assign a certain tag, correspondent, document
+    type, or storage path. This will usually be the case as you start
+    filling up paperless with documents. Example: If all your documents
+    are either from "Webshop" or "Bank", paperless will assign one
+    of these correspondents to ANY new document, if both are set to
+    automatic matching.
 
 ## Hooking into the consumption process {#consume-hooks}
 
 Sometimes you may want to do something arbitrary whenever a document is
 consumed. Rather than try to predict what you may want to do, Paperless
 lets you execute scripts of your own choosing just before or after a
-document is consumed using a couple simple hooks.
+document is consumed using a couple of simple hooks.
 
 Just write a script, put it somewhere that Paperless can read & execute,
 and then put the path to that script in `paperless.conf` or
 `docker-compose.env` with the variable name of either
-`PAPERLESS_PRE_CONSUME_SCRIPT` or `PAPERLESS_POST_CONSUME_SCRIPT`.
+[`PAPERLESS_PRE_CONSUME_SCRIPT`](configuration.md#PAPERLESS_PRE_CONSUME_SCRIPT) or [`PAPERLESS_POST_CONSUME_SCRIPT`](configuration.md#PAPERLESS_POST_CONSUME_SCRIPT).
 
 !!! info
 
@@ -126,6 +127,7 @@ script can access the following relevant environment variables set:
 | ----------------------- | ------------------------------------------------------------ |
 | `DOCUMENT_SOURCE_PATH`  | Original path of the consumed document                       |
 | `DOCUMENT_WORKING_PATH` | Path to a copy of the original that consumption will work on |
+| `TASK_ID`               | UUID of the task used to process the new document (if any)   |
 
 !!! note
 
@@ -134,6 +136,11 @@ script can access the following relevant environment variables set:
     be triggered, leading to failures as two tasks work on the
     same document path
 
+!!! warning
+
+    If your script modifies `DOCUMENT_WORKING_PATH` in a non-deterministic
+    way, this may allow duplicate documents to be stored
+
 A simple but common example for this would be creating a simple script
 like this:
 
@@ -168,21 +175,23 @@ Executed after the consumer has successfully processed a document and
 has moved it into paperless. It receives the following environment
 variables:
 
-| Environment Variable         | Description                                   |
-| ---------------------------- | --------------------------------------------- |
-| `DOCUMENT_ID`                | Database primary key of the document          |
-| `DOCUMENT_FILE_NAME`         | Formatted filename, not including paths       |
-| `DOCUMENT_CREATED`           | Date & time when document created             |
-| `DOCUMENT_MODIFIED`          | Date & time when document was last modified   |
-| `DOCUMENT_ADDED`             | Date & time when document was added           |
-| `DOCUMENT_SOURCE_PATH`       | Path to the original document file            |
-| `DOCUMENT_ARCHIVE_PATH`      | Path to the generate archive file (if any)    |
-| `DOCUMENT_THUMBNAIL_PATH`    | Path to the generated thumbnail               |
-| `DOCUMENT_DOWNLOAD_URL`      | URL for document download                     |
-| `DOCUMENT_THUMBNAIL_URL`     | URL for the document thumbnail                |
-| `DOCUMENT_CORRESPONDENT`     | Assigned correspondent (if any)               |
-| `DOCUMENT_TAGS`              | Comma separated list of tags applied (if any) |
-| `DOCUMENT_ORIGINAL_FILENAME` | Filename of original document                 |
+| Environment Variable         | Description                                    |
+| ---------------------------- | ---------------------------------------------- |
+| `DOCUMENT_ID`                | Database primary key of the document           |
+| `DOCUMENT_FILE_NAME`         | Formatted filename, not including paths        |
+| `DOCUMENT_CREATED`           | Date & time when document created              |
+| `DOCUMENT_MODIFIED`          | Date & time when document was last modified    |
+| `DOCUMENT_ADDED`             | Date & time when document was added            |
+| `DOCUMENT_SOURCE_PATH`       | Path to the original document file             |
+| `DOCUMENT_ARCHIVE_PATH`      | Path to the generate archive file (if any)     |
+| `DOCUMENT_THUMBNAIL_PATH`    | Path to the generated thumbnail                |
+| `DOCUMENT_DOWNLOAD_URL`      | URL for document download                      |
+| `DOCUMENT_THUMBNAIL_URL`     | URL for the document thumbnail                 |
+| `DOCUMENT_OWNER`             | Username of the document owner (if any)        |
+| `DOCUMENT_CORRESPONDENT`     | Assigned correspondent (if any)                |
+| `DOCUMENT_TAGS`              | Comma separated list of tags applied (if any)  |
+| `DOCUMENT_ORIGINAL_FILENAME` | Filename of original document                  |
+| `TASK_ID`                    | Task UUID used to import the document (if any) |
 
 The script can be in any language, A simple shell script example:
 
@@ -197,7 +206,7 @@ The script can be in any language, A simple shell script example:
 !!! warning
 
     The post consumption script should not modify the document files
-    directly
+    directly.
 
 The script's stdout and stderr will be logged line by line to the
 webserver log, along with the exit code of the script.
@@ -233,12 +242,12 @@ webserver:
 
 Troubleshooting:
 
-- Monitor the docker-compose log
-  `cd ~/paperless-ngx; docker-compose logs -f`
-- Check your script's permission e.g. in case of permission error
-  `sudo chmod 755 post-consumption-example.sh`
-- Pipe your scripts's output to a log file e.g.
-  `echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log`
+-   Monitor the Docker Compose log
+    `cd ~/paperless-ngx; docker compose logs -f`
+-   Check your script's permission e.g. in case of permission error
+    `sudo chmod 755 post-consumption-example.sh`
+-   Pipe your scripts's output to a log file e.g.
+    `echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log`
 
 ## File name handling {#file-name-handling}
 
@@ -248,14 +257,15 @@ document. You will end up getting files like `0000123.pdf` in your media
 directory. This isn't necessarily a bad thing, because you normally
 don't have to access these files manually. However, if you wish to name
 your files differently, you can do that by adjusting the
-`PAPERLESS_FILENAME_FORMAT` configuration option. Paperless adds the
+[`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) configuration option
+or using [storage paths (see below)](#storage-paths). Paperless adds the
 correct file extension e.g. `.pdf`, `.jpg` automatically.
 
 This variable allows you to configure the filename (folders are allowed)
 using placeholders. For example, configuring this to
 
 ```bash
-PAPERLESS_FILENAME_FORMAT={created_year}/{correspondent}/{title}
+PAPERLESS_FILENAME_FORMAT={{ created_year }}/{{ correspondent }}/{{ title }}
 ```
 
 will create a directory structure as follows:
@@ -281,36 +291,57 @@ will create a directory structure as follows:
     paperless will report your files as missing and won't be able to find
     them.
 
-Paperless provides the following placeholders within filenames:
+!!! tip
 
-- `{asn}`: The archive serial number of the document, or "none".
-- `{correspondent}`: The name of the correspondent, or "none".
-- `{document_type}`: The name of the document type, or "none".
-- `{tag_list}`: A comma separated list of all tags assigned to the
-  document.
-- `{title}`: The title of the document.
-- `{created}`: The full date (ISO format) the document was created.
-- `{created_year}`: Year created only, formatted as the year with
-  century.
-- `{created_year_short}`: Year created only, formatted as the year
-  without century, zero padded.
-- `{created_month}`: Month created only (number 01-12).
-- `{created_month_name}`: Month created name, as per locale
-- `{created_month_name_short}`: Month created abbreviated name, as per
-  locale
-- `{created_day}`: Day created only (number 01-31).
-- `{added}`: The full date (ISO format) the document was added to
-  paperless.
-- `{added_year}`: Year added only.
-- `{added_year_short}`: Year added only, formatted as the year without
-  century, zero padded.
-- `{added_month}`: Month added only (number 01-12).
-- `{added_month_name}`: Month added name, as per locale
-- `{added_month_name_short}`: Month added abbreviated name, as per
-  locale
-- `{added_day}`: Day added only (number 01-31).
-- `{owner_username}`: Username of document owner, if any, or "none"
-- `{original_name}`: Document original filename, minus the extension, if any, or "none"
+    Paperless checks the filename of a document whenever it is saved. Changing (or deleting)
+    a [storage path](#storage-paths) will automatically be reflected in the file system. However,
+    when changing `PAPERLESS_FILENAME_FORMAT` you will need to manually run the
+    [`document renamer`](administration.md#renamer) to move any existing documents.
+
+### Placeholders {#filename-format-variables}
+
+Paperless provides the following variables for use within filenames:
+
+-   `{{ asn }}`: The archive serial number of the document, or "none".
+-   `{{ correspondent }}`: The name of the correspondent, or "none".
+-   `{{ document_type }}`: The name of the document type, or "none".
+-   `{{ tag_list }}`: A comma separated list of all tags assigned to the
+    document.
+-   `{{ title }}`: The title of the document.
+-   `{{ created }}`: The full date (ISO format) the document was created.
+-   `{{ created_year }}`: Year created only, formatted as the year with
+    century.
+-   `{{ created_year_short }}`: Year created only, formatted as the year
+    without century, zero padded.
+-   `{{ created_month }}`: Month created only (number 01-12).
+-   `{{ created_month_name }}`: Month created name, as per locale
+-   `{{ created_month_name_short }}`: Month created abbreviated name, as per
+    locale
+-   `{{ created_day }}`: Day created only (number 01-31).
+-   `{{ added }}`: The full date (ISO format) the document was added to
+    paperless.
+-   `{{ added_year }}`: Year added only.
+-   `{{ added_year_short }}`: Year added only, formatted as the year without
+    century, zero padded.
+-   `{{ added_month }}`: Month added only (number 01-12).
+-   `{{ added_month_name }}`: Month added name, as per locale
+-   `{{ added_month_name_short }}`: Month added abbreviated name, as per
+    locale
+-   `{{ added_day }}`: Day added only (number 01-31).
+-   `{{ owner_username }}`: Username of document owner, if any, or "none"
+-   `{{ original_name }}`: Document original filename, minus the extension, if any, or "none"
+-   `{{ doc_pk }}`: The paperless identifier (primary key) for the document.
+
+!!! warning
+
+    When using file name placeholders, in particular when using `{tag_list}`,
+    you may run into the limits of your operating system's maximum path lengths.
+    In that case, files will retain the previous path instead and the issue logged.
+
+!!! tip
+
+    These variables are all simple strings, but the format can be a full template.
+    See [Filename Templates](#filename-templates) for even more advanced formatting.
 
 Paperless will try to conserve the information from your database as
 much as possible. However, some characters that you can use in document
@@ -322,34 +353,12 @@ paperless will automatically append `_01`, `_02`, etc to the filename.
 This happens if all the placeholders in a filename evaluate to the same
 value.
 
-!!! tip
-
-    You can affect how empty placeholders are treated by changing the
-    following setting to `true`.
-
-    ```
-    PAPERLESS_FILENAME_FORMAT_REMOVE_NONE=True
-    ```
-
-    Doing this results in all empty placeholders resolving to "" instead
-    of "none" as stated above. Spaces before empty placeholders are
-    removed as well, empty directories are omitted.
-
-!!! tip
-
-    Paperless checks the filename of a document whenever it is saved.
-    Therefore, you need to update the filenames of your documents and move
-    them after altering this setting by invoking the
-    [`document renamer`](/administration#renamer).
-
-!!! warning
-
-    Make absolutely sure you get the spelling of the placeholders right, or
-    else paperless will use the default naming scheme instead.
+If there are any errors in the placeholders included in `PAPERLESS_FILENAME_FORMAT`,
+paperless will fall back to using the default naming scheme instead.
 
 !!! caution
 
-    As of now, you could totally tell paperless to store your files anywhere
+    As of now, you could potentially tell paperless to store your files anywhere
     outside the media directory by setting
 
     ```
@@ -357,28 +366,25 @@ value.
     ```
 
     However, keep in mind that inside docker, if files get stored outside of
-    the predefined volumes, they will be lost after a restart of paperless.
+    the predefined volumes, they will be lost after a restart.
 
-!!! warning
+#### Empty placeholders
 
-    When file naming handling, in particular when using `{tag_list}`,
-    you may run into the limits of your operating system's maximum
-    path lengths.  Files will retain the previous path instead and
-    the issue logged.
+You can affect how empty placeholders are treated by changing the
+[`PAPERLESS_FILENAME_FORMAT_REMOVE_NONE`](configuration.md#PAPERLESS_FILENAME_FORMAT_REMOVE_NONE) setting.
 
-## Storage paths
+Enabling this results in all empty placeholders resolving to "" instead of "none" as stated above. Spaces
+before empty placeholders are removed as well, empty directories are omitted.
 
-One of the best things in Paperless is that you can not only access the
-documents via the web interface, but also via the file system.
+### Storage paths
 
-When a single storage layout is not sufficient for your use case,
-storage paths come to the rescue. Storage paths allow you to configure
-more precisely where each document is stored in the file system.
+When a single storage layout is not sufficient for your use case, storage paths allow for more complex
+structure to set precisely where each document is stored in the file system.
 
-- Each storage path is a `PAPERLESS_FILENAME_FORMAT` and
-  follows the rules described above
-- Each document is assigned a storage path using the matching
-  algorithms described above, but can be overwritten at any time
+-   Each storage path is a [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) and
+    follows the rules described above
+-   Each document is assigned a storage path using the matching algorithms described above, but can be
+    overwritten at any time
 
 For example, you could define the following two storage paths:
 
@@ -389,8 +395,8 @@ For example, you could define the following two storage paths:
     the correspondence.
 
 ```
-By Year = {created_year}/{correspondent}/{title}
-Insurances = Insurances/{correspondent}/{created_year}-{created_month}-{created_day} {title}
+By Year = {{ created_year }}/{{ correspondent }}/{{ title }}
+Insurances = Insurances/{{ correspondent }}/{{ created_year }}-{{ created_month }}-{{ created_day }} {{ title }}
 ```
 
 If you then map these storage paths to the documents, you might get the
@@ -415,7 +421,98 @@ Insurances/                             # Insurances
 !!! tip
 
     Defining a storage path is optional. If no storage path is defined for a
-    document, the global `PAPERLESS_FILENAME_FORMAT` is applied.
+    document, the global [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) is applied.
+
+### Filename Templates {#filename-templates}
+
+The filename formatting uses [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/) to build the filename.
+This allows for complex logic to be included in the format, including [logical structures](https://jinja.palletsprojects.com/en/3.1.x/templates/#list-of-control-structures)
+and [filters](https://jinja.palletsprojects.com/en/3.1.x/templates/#id11) to manipulate the [variables](#filename-format-variables)
+provided. The template is provided as a string, potentially multiline, and rendered into a single line.
+
+In addition, the entire Document instance is available to be utilized in a more advanced way, as well as some variables which only make sense to be accessed
+with more complex logic.
+
+#### Additional Variables
+
+-   `{{ tag_name_list }}`: A list of tag names applied to the document, ordered by the tag name. Note this is a list, not a single string
+-   `{{ custom_fields }}`: A mapping of custom field names to their type and value. A user can access the mapping by field name or check if a field is applied by checking its existence in the variable.
+
+!!! tip
+
+    To access a custom field which has a space in the name, use the `get_cf_value` filter.  See the examples below.
+    This helps get fields by name and handle a default value if the named field is not attached to a Document.
+
+#### Examples
+
+This example will construct a path based on the archive serial number range:
+
+```jinja
+somepath/
+{% if document.archive_serial_number >= 0 and document.archive_serial_number <= 200 %}
+  asn-000-200/{{title}}
+{% elif document.archive_serial_number >= 201 and document.archive_serial_number <= 400 %}
+  asn-201-400
+  {% if document.archive_serial_number >= 201 and document.archive_serial_number < 300 %}
+    /asn-2xx
+  {% elif document.archive_serial_number >= 300 and document.archive_serial_number < 400 %}
+    /asn-3xx
+  {% endif %}
+{% endif %}
+/{{ title }}
+```
+
+For a document with an ASN of 205, it would result in `somepath/asn-201-400/asn-2xx/Title.pdf`, but
+a document with an ASN of 355 would be placed in `somepath/asn-201-400/asn-3xx/Title.pdf`.
+
+```jinja
+{% if document.mime_type == "application/pdf" %}
+  pdfs
+{% elif document.mime_type == "image/png" %}
+  pngs
+{% else %}
+  others
+{% endif %}
+/{{ title }}
+```
+
+For a PDF document, it would result in `pdfs/Title.pdf`, but for a PNG document, the path would be `pngs/Title.pdf`.
+
+To use custom fields:
+
+```jinja
+{% if "Invoice" in custom_fields %}
+  invoices/{{ custom_fields.Invoice.value }}
+{% else %}
+  not-invoices/{{ title }}
+{% endif %}
+```
+
+If the document has a custom field named "Invoice" with a value of 123, it would be filed into the `invoices/123.pdf`, but a document without the custom field
+would be filed to `not-invoices/Title.pdf`
+
+If the custom field is named "Invoice Number", you would access the value of it via the `get_cf_value` filter due to quirks of the Django Template Language:
+
+```jinja
+"invoices/{{ custom_fields|get_cf_value('Invoice Number') }}"
+```
+
+You can also use a custom `datetime` filter to format dates:
+
+```jinja
+invoices/
+{{ custom_fields|get_cf_value("Date Field","2024-01-01")|datetime('%Y') }}/
+{{ custom_fields|get_cf_value("Date Field","2024-01-01")|datetime('%m') }}/
+{{ custom_fields|get_cf_value("Date Field","2024-01-01")|datetime('%d') }}/
+Invoice_{{ custom_fields|get_cf_value("Select Field") }}_{{ custom_fields|get_cf_value("Date Field","2024-01-01")|replace("-", "") }}.pdf
+```
+
+This will create a path like `invoices/2022/01/01/Invoice_OptionTwo_20220101.pdf` if the custom field "Date Field" is set to January 1, 2022 and "Select Field" is set to `OptionTwo`.
+
+## Automatic recovery of invalid PDFs {#pdf-recovery}
+
+Paperless will attempt to "clean" certain invalid PDFs with `qpdf` before processing if, for example, the mime_type
+detection is incorrect. This can happen if the PDF is not properly formatted or contains errors.
 
 ## Celery Monitoring {#celery-monitoring}
 
@@ -425,25 +522,29 @@ to view more detailed information about the health of the celery workers
 used for asynchronous tasks. This includes details on currently running,
 queued and completed tasks, timing and more. Flower can also be used
 with Prometheus, as it exports metrics. For details on its capabilities,
-refer to the Flower documentation.
+refer to the [Flower](https://flower.readthedocs.io/en/latest/index.html)
+documentation.
 
+Flower can be enabled with the setting [PAPERLESS_ENABLE_FLOWER](configuration.md#PAPERLESS_ENABLE_FLOWER).
 To configure Flower further, create a `flowerconfig.py` and
 place it into the `src/paperless` directory. For a Docker
 installation, you can use volumes to accomplish this:
 
 ```yaml
 services:
-  # ...
-  webserver:
-    ports:
-      - 5555:5555 # (2)!
     # ...
-    volumes:
-      - /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro # (1)!
+    webserver:
+        environment:
+            - PAPERLESS_ENABLE_FLOWER
+        ports:
+            - 5555:5555 # (2)!
+        # ...
+        volumes:
+            - /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro # (1)!
 ```
 
 1. Note the `:ro` tag means the file will be mounted as read only.
-2. `flower` runs by default on port 5555, but this can be configured
+2. By default, Flower runs on port 5555, but this can be configured.
 
 ## Custom Container Initialization
 
@@ -470,11 +571,11 @@ For example, using Docker Compose:
 
 ```yaml
 services:
-  # ...
-  webserver:
     # ...
-    volumes:
-      - /path/to/my/scripts:/custom-cont-init.d:ro # (1)!
+    webserver:
+        # ...
+        volumes:
+            - /path/to/my/scripts:/custom-cont-init.d:ro # (1)!
 ```
 
 1. Note the `:ro` tag means the folder will be mounted as read only. This is for extra security against changes
@@ -504,31 +605,43 @@ existing tables) with:
     an older system may fix issues that can arise while setting up Paperless-ngx but
     `utf8mb3` can cause issues with consumption (where `utf8mb4` does not).
 
+### Missing timezones
+
+MySQL as well as MariaDB do not have any timezone information by default (though some
+docker images such as the official MariaDB image take care of this for you) which will
+cause unexpected behavior with date-based queries.
+
+To fix this, execute one of the following commands:
+
+MySQL: `mysql_tzinfo_to_sql /usr/share/zoneinfo | mysql -u root mysql -p`
+
+MariaDB: `mariadb-tzinfo-to-sql /usr/share/zoneinfo | mariadb -u root mysql -p`
+
 ## Barcodes {#barcodes}
 
-Paperless is able to utilize barcodes for automatically preforming some tasks.
+Paperless is able to utilize barcodes for automatically performing some tasks.
 
 At this time, the library utilized for detection of barcodes supports the following types:
 
-- AN-13/UPC-A
-- UPC-E
-- EAN-8
-- Code 128
-- Code 93
-- Code 39
-- Codabar
-- Interleaved 2 of 5
-- QR Code
-- SQ Code
+-   AN-13/UPC-A
+-   UPC-E
+-   EAN-8
+-   Code 128
+-   Code 93
+-   Code 39
+-   Codabar
+-   Interleaved 2 of 5
+-   QR Code
+-   SQ Code
 
 You may check for updates on the [zbar library homepage](https://github.com/mchehab/zbar).
 For usage in Paperless, the type of barcode does not matter, only the contents of it.
 
-For how to enable barcode usage, see [the configuration](/configuration#barcodes).
+For how to enable barcode usage, see [the configuration](configuration.md#barcodes).
 The two settings may be enabled independently, but do have interactions as explained
 below.
 
-### Document Splitting
+### Document Splitting {#document-splitting}
 
 When enabled, Paperless will look for a barcode with the configured value and create a new document
 starting from the next page. The page with the barcode on it will _not_ be retained. It
@@ -543,3 +656,187 @@ If document splitting via barcode is also enabled, documents will be split when
 barcode is located. However, differing from the splitting, the page with the
 barcode _will_ be retained. This allows application of a barcode to any page, including
 one which holds data to keep in the document.
+
+### Tag Assignment
+
+When enabled, Paperless will parse barcodes and attempt to interpret and assign tags.
+
+See the relevant settings [`PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE`](configuration.md#PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE)
+and [`PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING`](configuration.md#PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING)
+for more information.
+
+## Automatic collation of double-sided documents {#collate}
+
+!!! note
+
+    If your scanner supports double-sided scanning natively, you do not need this feature.
+
+This feature is turned off by default, see [configuration](configuration.md#collate) on how to turn it on.
+
+### Summary
+
+If you have a scanner with an automatic document feeder (ADF) that only scans a single side,
+this feature makes scanning double-sided documents much more convenient by automatically
+collating two separate scans into one document, reordering the pages as necessary.
+
+### Usage example
+
+Suppose you have a double-sided document with 6 pages (3 sheets of paper). First,
+put the stack into your ADF as normal, ensuring that page 1 is scanned first. Your ADF
+will now scan pages 1, 3, and 5. Then you (or your scanner, if it supports it) upload
+the scan into the correct sub-directory of the consume folder (`double-sided` by default;
+keep in mind that Paperless will _not_ automatically create the directory for you.)
+Paperless will then process the scan and move it into an internal staging area.
+
+The next step is to turn your stack upside down (without reordering the sheets of paper),
+and scan it once again, your ADF will now scan pages 6, 4, and 2, in that order. Once this
+scan is copied into the sub-directory, Paperless will collate the previous scan with the
+new one, reversing the order of the pages on the second, "even numbered" scan. The
+resulting document will have the pages 1-6 in the correct order, and this new file will
+then be processed as normal.
+
+!!! tip
+
+    When scanning the even numbered pages, you can omit the last empty pages, if there are
+    any. For example, if page 6 is empty, you only need to scan pages 2 and 4. _Do not_ omit
+    empty pages in the middle of the document.
+
+### Things that could go wrong
+
+Paperless will notice when the first, "odd numbered" scan has less pages than the second
+scan (this can happen when e.g. the ADF skipped a few pages in the first pass). In that
+case, Paperless will remove the staging copy as well as the scan, and give you an error
+message asking you to restart the process from scratch, by scanning the odd pages again,
+followed by the even pages.
+
+It's important that the scan files get consumed in the correct order, and one at a time.
+You therefore need to make sure that Paperless is running while you upload the files into
+the directory; and if you're using [polling](configuration.md#polling), make sure that
+`CONSUMER_POLLING` is set to a value lower than it takes for the second scan to appear,
+like 5-10 or even lower.
+
+Another thing that might happen is that you start a double sided scan, but then forget
+to upload the second file. To avoid collating the wrong documents if you then come back
+a day later to scan a new double-sided document, Paperless will only keep an "odd numbered
+pages" file for up to 30 minutes. If more time passes, it will consider the next incoming
+scan a completely new "odd numbered pages" one. The old staging file will get discarded.
+
+### Interaction with "subdirs as tags"
+
+The collation feature can be used together with the [subdirs as tags](configuration.md#consume_config)
+feature (but this is not a requirement). Just create a correctly named double-sided subdir
+in the hierarchy and upload your scans there. For example, both `double-sided/foo/bar` as
+well as `foo/bar/double-sided` will cause the collated document to be treated as if it
+were uploaded into `foo/bar` and receive both `foo` and `bar` tags, but not `double-sided`.
+
+### Interaction with document splitting
+
+You can use the [document splitting](#document-splitting) feature, but if you use a normal
+single-sided split marker page, the split document(s) will have an empty page at the front (or
+whatever else was on the backside of the split marker page.) You can work around that by having
+a split marker page that has the split barcode on _both_ sides. This way, the extra page will
+get automatically removed.
+
+## SSO and third party authentication with Paperless-ngx
+
+Paperless-ngx has a built-in authentication system from Django but you can easily integrate an
+external authentication solution using one of the following methods:
+
+### Remote User authentication
+
+This is a simple option that uses remote user authentication made available by certain SSO
+applications. See the relevant configuration options for more information:
+[PAPERLESS_ENABLE_HTTP_REMOTE_USER](configuration.md#PAPERLESS_ENABLE_HTTP_REMOTE_USER),
+[PAPERLESS_HTTP_REMOTE_USER_HEADER_NAME](configuration.md#PAPERLESS_HTTP_REMOTE_USER_HEADER_NAME)
+and [PAPERLESS_LOGOUT_REDIRECT_URL](configuration.md#PAPERLESS_LOGOUT_REDIRECT_URL)
+
+### OpenID Connect and social authentication
+
+Version 2.5.0 of Paperless-ngx added support for integrating other authentication systems via
+the [django-allauth](https://github.com/pennersr/django-allauth) package. Once set up, users
+can either log in or (optionally) sign up using any third party systems you integrate. See the
+relevant [configuration settings](configuration.md#PAPERLESS_SOCIALACCOUNT_PROVIDERS) and
+[django-allauth docs](https://docs.allauth.org/en/latest/socialaccount/configuration.html)
+for more information.
+
+To associate an existing Paperless-ngx account with a social account, first login with your
+regular credentials and then choose "My Profile" from the user dropdown in the app and you
+will see options to connect social account(s). If enabled, signup options will be available
+on the login page.
+
+As an example, to set up login via Github, the following environment variables would need to be
+set:
+
+```conf
+PAPERLESS_APPS="allauth.socialaccount.providers.github"
+PAPERLESS_SOCIALACCOUNT_PROVIDERS='{"github": {"APPS": [{"provider_id": "github","name": "Github","client_id": "<CLIENT_ID>","secret": "<CLIENT_SECRET>"}]}}'
+```
+
+Or, to use OpenID Connect ("OIDC"), via Keycloak in this example:
+
+```conf
+PAPERLESS_APPS="allauth.socialaccount.providers.openid_connect"
+PAPERLESS_SOCIALACCOUNT_PROVIDERS='
+{"openid_connect": {"APPS": [{"provider_id": "keycloak","name": "Keycloak","client_id": "paperless","secret": "<CLIENT_SECRET>","settings": { "server_url": "https://<KEYCLOAK_SERVER>/realms/<REALM>/.well-known/openid-configuration"}}]}}'
+```
+
+More details about configuration option for various providers can be found in the [allauth documentation](https://docs.allauth.org/en/latest/socialaccount/providers/index.html#provider-specifics).
+
+### Disabling Regular Login
+
+Once external auth is set up, 'regular' login can be disabled with the [PAPERLESS_DISABLE_REGULAR_LOGIN](configuration.md#PAPERLESS_DISABLE_REGULAR_LOGIN) setting and / or users can be automatically
+redirected with the [PAPERLESS_REDIRECT_LOGIN_TO_SSO](configuration.md#PAPERLESS_REDIRECT_LOGIN_TO_SSO) setting.
+
+## Decryption of encrypted emails before consumption {#gpg-decryptor}
+
+Paperless-ngx can be configured to decrypt gpg encrypted emails before consumption.
+
+### Requirements
+
+You need a recent version of `gpg-agent >= 2.1.1` installed on your host.
+Your host needs to be setup for decrypting your emails via `gpg-agent`, see this [tutorial](https://www.digitalocean.com/community/tutorials/how-to-use-gpg-to-encrypt-and-sign-messages#encrypt-and-decrypt-messages-with-gpg) for instance.
+Test your setup and make sure that you can encrypt and decrypt files using your key
+
+```
+gpg --encrypt --armor -r person@email.com name_of_file
+gpg --decrypt name_of_file.asc
+```
+
+### Setup
+
+First, enable the [PAPERLESS_ENABLE_GPG_DECRYPTOR environment variable](configuration.md#PAPERLESS_ENABLE_GPG_DECRYPTOR).
+
+Then determine your local `gpg-agent.extra` socket by invoking
+
+```
+gpgconf --list-dir agent-extra-socket
+```
+
+on your host. A possible output is `~/.gnupg/S.gpg-agent.extra`.
+Also find the location of your public keyring.
+
+If using docker, you'll need to add the following volume mounts to your `docker-compose.yml` file:
+
+```yaml
+webserver:
+    volumes:
+        - /home/user/.gnupg/pubring.gpg:/usr/src/paperless/.gnupg/pubring.gpg
+        - <path to gpg-agent.extra socket>:/usr/src/paperless/.gnupg/S.gpg-agent
+```
+
+For a 'bare-metal' installation no further configuration is necessary. If you
+want to use a separate `GNUPG_HOME`, you can do so by configuring the [PAPERLESS_EMAIL_GNUPG_HOME environment variable](configuration.md#PAPERLESS_EMAIL_GNUPG_HOME).
+
+### Troubleshooting
+
+-   Make sure, that `gpg-agent` is running on your host machine
+-   Make sure, that encryption and decryption works from inside the container using the `gpg` commands from above.
+-   Check that all files in `/usr/src/paperless/.gnupg` have correct permissions
+
+```shell
+paperless@9da1865df327:~/.gnupg$ ls -al
+drwx------ 1 paperless paperless   4096 Aug 18 17:52 .
+drwxr-xr-x 1 paperless paperless   4096 Aug 18 17:52 ..
+srw------- 1 paperless paperless      0 Aug 18 17:22 S.gpg-agent
+-rw------- 1 paperless paperless 147940 Jul 24 10:23 pubring.gpg
+```

docs/api.md

@@ -6,19 +6,25 @@ provides a browsable API for most of its endpoints, which you can
 inspect at `http://<paperless-host>:<port>/api/`. This also documents
 most of the available filters and ordering fields.
 
-The API provides 7 main endpoints:
+The API provides the following main endpoints:
 
-- `/api/documents/`: Full CRUD support, except POSTing new documents.
-  See below.
-- `/api/correspondents/`: Full CRUD support.
-- `/api/document_types/`: Full CRUD support.
-- `/api/logs/`: Read-Only.
-- `/api/tags/`: Full CRUD support.
-- `/api/tasks/`: Read-only.
-- `/api/mail_accounts/`: Full CRUD support.
-- `/api/mail_rules/`: Full CRUD support.
-- `/api/users/`: Full CRUD support.
-- `/api/groups/`: Full CRUD support.
+-   `/api/correspondents/`: Full CRUD support.
+-   `/api/custom_fields/`: Full CRUD support.
+-   `/api/documents/`: Full CRUD support, except POSTing new documents.
+    See [below](#file-uploads).
+-   `/api/document_types/`: Full CRUD support.
+-   `/api/groups/`: Full CRUD support.
+-   `/api/logs/`: Read-Only.
+-   `/api/mail_accounts/`: Full CRUD support.
+-   `/api/mail_rules/`: Full CRUD support.
+-   `/api/profile/`: GET, PATCH
+-   `/api/share_links/`: Full CRUD support.
+-   `/api/storage_paths/`: Full CRUD support.
+-   `/api/tags/`: Full CRUD support.
+-   `/api/tasks/`: Read-only.
+-   `/api/users/`: Full CRUD support.
+-   `/api/workflows/`: Full CRUD support.
+-   `/api/search/` GET, see [below](#global-search).
 
 All of these endpoints except for the logging endpoint allow you to
 fetch (and edit and delete where appropriate) individual objects by
@@ -27,39 +33,47 @@ appending their primary key to the path, e.g. `/api/documents/454/`.
 The objects served by the document endpoint contain the following
 fields:
 
-- `id`: ID of the document. Read-only.
-- `title`: Title of the document.
-- `content`: Plain text content of the document.
-- `tags`: List of IDs of tags assigned to this document, or empty
-  list.
-- `document_type`: Document type of this document, or null.
-- `correspondent`: Correspondent of this document or null.
-- `created`: The date time at which this document was created.
-- `created_date`: The date (YYYY-MM-DD) at which this document was
-  created. Optional. If also passed with created, this is ignored.
-- `modified`: The date at which this document was last edited in
-  paperless. Read-only.
-- `added`: The date at which this document was added to paperless.
-  Read-only.
-- `archive_serial_number`: The identifier of this document in a
-  physical document archive.
-- `original_file_name`: Verbose filename of the original document.
-  Read-only.
-- `archived_file_name`: Verbose filename of the archived document.
-  Read-only. Null if no archived document is available.
-- `set_permissions`: Allows setting document permissions. Optional,
-  write-only. See [below](#permissions).
+-   `id`: ID of the document. Read-only.
+-   `title`: Title of the document.
+-   `content`: Plain text content of the document.
+-   `tags`: List of IDs of tags assigned to this document, or empty
+    list.
+-   `document_type`: Document type of this document, or null.
+-   `correspondent`: Correspondent of this document or null.
+-   `created`: The date time at which this document was created.
+-   `created_date`: The date (YYYY-MM-DD) at which this document was
+    created. Optional. If also passed with created, this is ignored.
+-   `modified`: The date at which this document was last edited in
+    paperless. Read-only.
+-   `added`: The date at which this document was added to paperless.
+    Read-only.
+-   `archive_serial_number`: The identifier of this document in a
+    physical document archive.
+-   `original_file_name`: Verbose filename of the original document.
+    Read-only.
+-   `archived_file_name`: Verbose filename of the archived document.
+    Read-only. Null if no archived document is available.
+-   `notes`: Array of notes associated with the document.
+-   `page_count`: Number of pages.
+-   `set_permissions`: Allows setting document permissions. Optional,
+    write-only. See [below](#permissions).
+-   `custom_fields`: Array of custom fields & values, specified as
+    `{ field: CUSTOM_FIELD_ID, value: VALUE }`
+
+!!! note
+
+    Note that all endpoint URLs must end with a `/`slash.
 
 ## Downloading documents
 
 In addition to that, the document endpoint offers these additional
 actions on individual documents:
 
-- `/api/documents/<pk>/download/`: Download the document.
-- `/api/documents/<pk>/preview/`: Display the document inline, without
-  downloading it.
-- `/api/documents/<pk>/thumb/`: Download the PNG thumbnail of a
-  document.
+-   `/api/documents/<pk>/download/`: Download the document.
+-   `/api/documents/<pk>/preview/`: Display the document inline, without
+    downloading it.
+-   `/api/documents/<pk>/thumb/`: Download the PNG thumbnail of a
+    document.
 
 Paperless generates archived PDF/A documents from consumed files and
 stores both the original files as well as the archived files. By
@@ -93,30 +107,30 @@ Access the metadata of a document with an ID `id` at
 
 The endpoint reports the following data:
 
-- `original_checksum`: MD5 checksum of the original document.
-- `original_size`: Size of the original document, in bytes.
-- `original_mime_type`: Mime type of the original document.
-- `media_filename`: Current filename of the document, under which it
-  is stored inside the media directory.
-- `has_archive_version`: True, if this document is archived, false
-  otherwise.
-- `original_metadata`: A list of metadata associated with the original
-  document. See below.
-- `archive_checksum`: MD5 checksum of the archived document, or null.
-- `archive_size`: Size of the archived document in bytes, or null.
-- `archive_metadata`: Metadata associated with the archived document,
-  or null. See below.
+-   `original_checksum`: MD5 checksum of the original document.
+-   `original_size`: Size of the original document, in bytes.
+-   `original_mime_type`: Mime type of the original document.
+-   `media_filename`: Current filename of the document, under which it
+    is stored inside the media directory.
+-   `has_archive_version`: True, if this document is archived, false
+    otherwise.
+-   `original_metadata`: A list of metadata associated with the original
+    document. See below.
+-   `archive_checksum`: MD5 checksum of the archived document, or null.
+-   `archive_size`: Size of the archived document in bytes, or null.
+-   `archive_metadata`: Metadata associated with the archived document,
+    or null. See below.
 
 File metadata is reported as a list of objects in the following form:
 
 ```json
 [
-  {
-    "namespace": "http://ns.adobe.com/pdf/1.3/",
-    "prefix": "pdf",
-    "key": "Producer",
-    "value": "SparklePDF, Fancy edition"
-  }
+    {
+        "namespace": "http://ns.adobe.com/pdf/1.3/",
+        "prefix": "pdf",
+        "key": "Producer",
+        "value": "SparklePDF, Fancy edition"
+    }
 ]
 ```
 
@@ -124,9 +138,15 @@ File metadata is reported as a list of objects in the following form:
 depends on the file type and the metadata available in that specific
 document. Paperless only reports PDF metadata at this point.
 
+## Documents additional endpoints
+
+-   `/api/documents/<id>/notes/`: Retrieve notes for a document.
+-   `/api/documents/<id>/share_links/`: Retrieve share links for a document.
+-   `/api/documents/<id>/history/`: Retrieve history of changes for a document.
+
 ## Authorization
 
-The REST api provides three different forms of authentication.
+The REST api provides four different forms of authentication.
 
 1.  Basic authentication
 
@@ -147,6 +167,10 @@ The REST api provides three different forms of authentication.
 
 3.  Token authentication
 
+    You can create (or re-create) an API token by opening the "My Profile"
+    link in the user dropdown found in the web UI and clicking the circular
+    arrow button.
+
     Paperless also offers an endpoint to acquire authentication tokens.
 
     POST a username and password as a form or json string to
@@ -158,7 +182,45 @@ The REST api provides three different forms of authentication.
     Authorization: Token <token>
     ```
 
-    Tokens can be managed and revoked in the paperless admin.
+    Tokens can also be managed in the Django admin.
+
+4.  Remote User authentication
+
+    If enabled (see
+    [configuration](configuration.md#PAPERLESS_ENABLE_HTTP_REMOTE_USER_API)),
+    you can authenticate against the API using Remote User auth.
+
+## Global search
+
+A global search endpoint is available at `/api/search/` and requires a search term
+of > 2 characters e.g. `?query=foo`. This endpoint returns a maximum of 3 results
+across nearly all objects, e.g. documents, tags, saved views, mail rules, etc.
+Results are only included if the requesting user has the appropriate permissions.
+
+Results are returned in the following format:
+
+```json
+{
+  total: number
+  documents: []
+  saved_views: []
+  correspondents: []
+  document_types: []
+  storage_paths: []
+  tags: []
+  users: []
+  groups: []
+  mail_accounts: []
+  mail_rules: []
+  custom_fields: []
+  workflows: []
+}
+```
+
+Global search first searches objects by name (or title for documents) matching the query.
+If the optional `db_only` parameter is set, only document titles will be searched. Otherwise,
+if the amount of documents returned by a simple title string search is < 3, results from the
+search index will also be included.
 
 ## Searching for documents
 
@@ -166,20 +228,14 @@ Full text searching is available on the `/api/documents/` endpoint. Two
 specific query parameters cause the API to return full text search
 results:
 
-- `/api/documents/?query=your%20search%20query`: Search for a document
-  using a full text query. For details on the syntax, see [Basic Usage - Searching](/usage#basic-usage_searching).
-- `/api/documents/?more_like=1234`: Search for documents similar to
-  the document with id 1234.
+-   `/api/documents/?query=your%20search%20query`: Search for a document
+    using a full text query. For details on the syntax, see [Basic Usage - Searching](usage.md#basic-usage_searching).
+-   `/api/documents/?more_like_id=1234`: Search for documents similar to
+    the document with id 1234.
 
 Pagination works exactly the same as it does for normal requests on this
 endpoint.
 
-Certain limitations apply to full text queries:
-
-- Results are always sorted by search score. The results matching the
-  query best will show up first.
-- Only a small subset of filtering parameters are supported.
-
 Furthermore, each returned document has an additional `__search_hit__`
 attribute with various information about the search results:
 
@@ -212,12 +268,57 @@ attribute with various information about the search results:
 }
 ```
 
-- `score` is an indication how well this document matches the query
-  relative to the other search results.
-- `highlights` is an excerpt from the document content and highlights
-  the search terms with `<span>` tags as shown above.
-- `rank` is the index of the search results. The first result will
-  have rank 0.
+-   `score` is an indication how well this document matches the query
+    relative to the other search results.
+-   `highlights` is an excerpt from the document content and highlights
+    the search terms with `<span>` tags as shown above.
+-   `rank` is the index of the search results. The first result will
+    have rank 0.
+
+### Filtering by custom fields
+
+You can filter documents by their custom field values by specifying the
+`custom_field_query` query parameter. Here are some recipes for common
+use cases:
+
+1. Documents with a custom field "due" (date) between Aug 1, 2024 and
+   Sept 1, 2024 (inclusive):
+
+    `?custom_field_query=["due", "range", ["2024-08-01", "2024-09-01"]]`
+
+2. Documents with a custom field "customer" (text) that equals "bob"
+   (case sensitive):
+
+    `?custom_field_query=["customer", "exact", "bob"]`
+
+3. Documents with a custom field "answered" (boolean) set to `true`:
+
+    `?custom_field_query=["answered", "exact", true]`
+
+4. Documents with a custom field "favorite animal" (select) set to either
+   "cat" or "dog":
+
+    `?custom_field_query=["favorite animal", "in", ["cat", "dog"]]`
+
+5. Documents with a custom field "address" (text) that is empty:
+
+    `?custom_field_query=["OR", ["address", "isnull", true], ["address", "exact", ""]]`
+
+6. Documents that don't have a field called "foo":
+
+    `?custom_field_query=["foo", "exists", false]`
+
+7. Documents that have document links "references" to both document 3 and 7:
+
+    `?custom_field_query=["references", "contains", [3, 7]]`
+
+All field types support basic operations including `exact`, `in`, `isnull`,
+and `exists`. String, URL, and monetary fields support case-insensitive
+substring matching operations including `icontains`, `istartswith`, and
+`iendswith`. Integer, float, and date fields support arithmetic comparisons
+including `gt` (>), `gte` (>=), `lt` (<), `lte` (<=), and `range`.
+Lastly, document link fields support a `contains` operator that behaves
+like a "is superset of" check.
 
 ### `/api/search/autocomplete/`
 
@@ -225,8 +326,8 @@ Get auto completions for a partial search term.
 
 Query parameters:
 
-- `term`: The incomplete term.
-- `limit`: Amount of results. Defaults to 10.
+-   `term`: The incomplete term.
+-   `limit`: Amount of results. Defaults to 10.
 
 Results returned by the endpoint are ordered by importance of the term
 in the document index. The first result is the term that has the highest
@@ -250,16 +351,19 @@ from there.
 
 The endpoint supports the following optional form fields:
 
-- `title`: Specify a title that the consumer should use for the
-  document.
-- `created`: Specify a DateTime where the document was created (e.g.
-  "2016-04-19" or "2016-04-19 06:15:00+02:00").
-- `correspondent`: Specify the ID of a correspondent that the consumer
-  should use for the document.
-- `document_type`: Similar to correspondent.
-- `tags`: Similar to correspondent. Specify this multiple times to
-  have multiple tags added to the document.
-- `archive_serial_number`: An optional archive serial number to set.
+-   `title`: Specify a title that the consumer should use for the
+    document.
+-   `created`: Specify a DateTime where the document was created (e.g.
+    "2016-04-19" or "2016-04-19 06:15:00+02:00").
+-   `correspondent`: Specify the ID of a correspondent that the consumer
+    should use for the document.
+-   `document_type`: Similar to correspondent.
+-   `storage_path`: Similar to correspondent.
+-   `tags`: Similar to correspondent. Specify this multiple times to
+    have multiple tags added to the document.
+-   `archive_serial_number`: An optional archive serial number to set.
+-   `custom_fields`: An array of custom field ids to assign (with an empty
+    value) to the document.
 
 The endpoint will immediately return HTTP 200 if the document consumption
 process was started successfully, with the UUID of the consumption task
@@ -272,40 +376,134 @@ consumption including the ID of a created document if consumption succeeded.
 ## Permissions
 
 All objects (documents, tags, etc.) allow setting object-level permissions
-with an optional `set_permissions` parameter which is of the form:
+with optional `owner` and / or a `set_permissions` parameters which are of
+the form:
 
 ```
-{
-  "owner": user_id,
-  "view": {
-      "users": [...],
-      "groups": [...],
-  },
-  "change": {
-      "users": [...],
-      "groups": [...],
-  },
+"owner": ...,
+"set_permissions": {
+    "view": {
+        "users": [...],
+        "groups": [...],
+    },
+    "change": {
+        "users": [...],
+        "groups": [...],
+    },
 }
 ```
 
-If this parameter is supplied the object's permissions will be overwritten,
+!!! note
+
+    Arrays should contain user or group ID numbers.
+
+If these parameters are supplied the object's permissions will be overwritten,
 assuming the authenticated user has permission to do so (the user must be
 the object owner or a superuser).
 
+### Retrieving full permissions
+
+By default, the API will return a truncated version of object-level
+permissions, returning `user_can_change` indicating whether the current user
+can edit the object (either because they are the object owner or have permissions
+granted). You can pass the parameter `full_perms=true` to API calls to view the
+full permissions of objects in a format that mirrors the `set_permissions`
+parameter above.
+
+## Bulk Editing
+
+The API supports various bulk-editing operations which are executed asynchronously.
+
+### Documents
+
+For bulk operations on documents, use the endpoint `/api/documents/bulk_edit/` which accepts
+a json payload of the format:
+
+```json
+{
+  "documents": [LIST_OF_DOCUMENT_IDS],
+  "method": METHOD, // see below
+  "parameters": args // see below
+}
+```
+
+The following methods are supported:
+
+-   `set_correspondent`
+    -   Requires `parameters`: `{ "correspondent": CORRESPONDENT_ID }`
+-   `set_document_type`
+    -   Requires `parameters`: `{ "document_type": DOCUMENT_TYPE_ID }`
+-   `set_storage_path`
+    -   Requires `parameters`: `{ "storage_path": STORAGE_PATH_ID }`
+-   `add_tag`
+    -   Requires `parameters`: `{ "tag": TAG_ID }`
+-   `remove_tag`
+    -   Requires `parameters`: `{ "tag": TAG_ID }`
+-   `modify_tags`
+    -   Requires `parameters`: `{ "add_tags": [LIST_OF_TAG_IDS] }` and / or `{ "remove_tags": [LIST_OF_TAG_IDS] }`
+-   `delete`
+    -   No `parameters` required
+-   `reprocess`
+    -   No `parameters` required
+-   `set_permissions`
+    -   Requires `parameters`:
+        -   `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
+        -   `"owner": OWNER_ID or null`
+        -   `"merge": true or false` (defaults to false)
+    -   The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
+        removing them) or be merged with existing permissions.
+-   `merge`
+    -   No additional `parameters` required.
+    -   The ordering of the merged document is determined by the list of IDs.
+    -   Optional `parameters`:
+        -   `"metadata_document_id": DOC_ID` apply metadata (tags, correspondent, etc.) from this document to the merged document.
+        -   `"delete_originals": true` to delete the original documents. This requires the calling user being the owner of
+            all documents that are merged.
+-   `split`
+    -   Requires `parameters`:
+        -   `"pages": [..]` The list should be a list of pages and/or a ranges, separated by commas e.g. `"[1,2-3,4,5-7]"`
+    -   Optional `parameters`:
+        -   `"delete_originals": true` to delete the original document after consumption. This requires the calling user being the owner of
+            the document.
+    -   The split operation only accepts a single document.
+-   `rotate`
+    -   Requires `parameters`:
+        -   `"degrees": DEGREES`. Must be an integer i.e. 90, 180, 270
+-   `delete_pages`
+    -   Requires `parameters`:
+        -   `"pages": [..]` The list should be a list of integers e.g. `"[2,3,4]"`
+    -   The delete_pages operation only accepts a single document.
+
+### Objects
+
+Bulk editing for objects (tags, document types etc.) currently supports set permissions or delete
+operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json payload of the format:
+
+```json
+{
+  "objects": [LIST_OF_OBJECT_IDS],
+  "object_type": "tags", "correspondents", "document_types" or "storage_paths",
+  "operation": "set_permissions" or "delete",
+  "owner": OWNER_ID, // optional
+  "permissions": { "view": { "users": [] ... }, "change": { ... } }, // (see 'set_permissions' format above)
+  "merge": true / false // defaults to false, see above
+}
+```
+
 ## API Versioning
 
 The REST API is versioned since Paperless-ngx 1.3.0.
 
-- Versioning ensures that changes to the API don't break older
-  clients.
-- Clients specify the specific version of the API they wish to use
-  with every request and Paperless will handle the request using the
-  specified API version.
-- Even if the underlying data model changes, older API versions will
-  always serve compatible data.
-- If no version is specified, Paperless will serve version 1 to ensure
-  compatibility with older clients that do not request a specific API
-  version.
+-   Versioning ensures that changes to the API don't break older
+    clients.
+-   Clients specify the specific version of the API they wish to use
+    with every request and Paperless will handle the request using the
+    specified API version.
+-   Even if the underlying data model changes, older API versions will
+    always serve compatible data.
+-   If no version is specified, Paperless will serve version 1 to ensure
+    compatibility with older clients that do not request a specific API
+    version.
 
 API versions are specified by submitting an additional HTTP `Accept`
 header with every request:
@@ -342,9 +540,19 @@ Initial API version.
 
 #### Version 2
 
-- Added field `Tag.color`. This read/write string field contains a hex
-  color such as `#a6cee3`.
-- Added read-only field `Tag.text_color`. This field contains the text
-  color to use for a specific tag, which is either black or white
-  depending on the brightness of `Tag.color`.
-- Removed field `Tag.colour`.
+-   Added field `Tag.color`. This read/write string field contains a hex
+    color such as `#a6cee3`.
+-   Added read-only field `Tag.text_color`. This field contains the text
+    color to use for a specific tag, which is either black or white
+    depending on the brightness of `Tag.color`.
+-   Removed field `Tag.colour`.
+
+#### Version 3
+
+-   Permissions endpoints have been added.
+-   The format of the `/api/ui_settings/` has changed.
+
+#### Version 4
+
+-   Consumption templates were refactored to workflows and API endpoints
+    changed as such.

docs/assets/extra.css

@@ -10,7 +10,7 @@
     --md-hue: 222;
 }
 
-@media (min-width: 400px) {
+@media (min-width: 768px) {
     .grid-left {
         width: 33%;
         float: left;
@@ -20,6 +20,28 @@
         margin-left: 4%;
         float: left;
     }
+
+    .grid-flipped-left {
+        width: 66%;
+        float: left;
+    }
+
+    .grid-flipped-right {
+        width: 29%;
+        margin-left: 4%;
+        float: left;
+    }
+
+    .grid-half-left {
+        width: 48%;
+        float: left;
+    }
+
+    .grid-half-right {
+        width: 48%;
+        margin-left: 4%;
+        float: left;
+    }
 }
 
 .grid-left > p {
@@ -31,6 +53,48 @@
     margin: 0;
 }
 
+.clear {
+    clear: both;
+    margin-bottom: 20px;
+    display: block;
+}
+
 .index-callout {
     margin-right: .5rem;
 }
+
+/* make code in headers not bold */
+h4 code {
+    font-weight: normal;
+}
+
+/* Hide config vars from sidebar, toc and move the border on mobile case their hidden */
+.md-nav.md-nav--secondary .md-nav__item .md-nav__link[href*="PAPERLESS_"],
+.md-nav.md-nav--secondary .md-nav__item .md-nav__link[href*="USERMAP_"] {
+    display: none;
+}
+
+@media screen and (max-width: 76.1875em) {
+    .md-nav--primary .md-nav__item {
+        border-top: none;
+    }
+
+    .md-nav--primary .md-nav__link {
+        border-top: .05rem solid var(--md-default-fg-color--lightest);
+    }
+}
+
+/* Show search shortcut key */
+[data-md-toggle="search"]:not(:checked) ~ .md-header .md-search__form::after {
+    position: absolute;
+    top: .3rem;
+    right: .3rem;
+    display: block;
+    padding: .1rem .4rem;
+    color: var(--md-default-fg-color--lighter);
+    font-weight: bold;
+    font-size: .8rem;
+    border: .05rem solid var(--md-default-fg-color--lighter);
+    border-radius: .1rem;
+    content: "/";
+  }

docs/development.md

@@ -6,23 +6,23 @@ on Paperless-ngx.
 Check out the source from GitHub. The repository is organized in the
 following way:
 
-- `main` always represents the latest release and will only see
-  changes when a new release is made.
-- `dev` contains the code that will be in the next release.
-- `feature-X` contain bigger changes that will be in some release, but
-  not necessarily the next one.
+-   `main` always represents the latest release and will only see
+    changes when a new release is made.
+-   `dev` contains the code that will be in the next release.
+-   `feature-X` contains bigger changes that will be in some release, but
+    not necessarily the next one.
 
 When making functional changes to Paperless-ngx, _always_ make your changes
 on the `dev` branch.
 
 Apart from that, the folder structure is as follows:
 
-- `docs/` - Documentation.
-- `src-ui/` - Code of the front end.
-- `src/` - Code of the back end.
-- `scripts/` - Various scripts that help with different parts of
-  development.
-- `docker/` - Files required to build the docker image.
+-   `docs/` - Documentation.
+-   `src-ui/` - Code of the front end.
+-   `src/` - Code of the back end.
+-   `scripts/` - Various scripts that help with different parts of
+    development.
+-   `docker/` - Files required to build the docker image.
 
 ## Contributing to Paperless-ngx
 
@@ -47,7 +47,7 @@ early on.
 Once installed, hooks will run when you commit. If the formatting isn't
 quite right or a linter catches something, the commit will be rejected.
 You'll need to look at the output and fix the issue. Some hooks, such
-as the Python formatting tool `black`, will format failing
+as the Python linting and formatting tool `ruff`, will format failing
 files, so all you need to do is `git add` those files again
 and retry your commit.
 
@@ -58,10 +58,10 @@ first-time setup.
 
 !!! note
 
-    Every command is executed directly from the root folder of the project unless specified otherwise.
+      Every command is executed directly from the root folder of the project unless specified otherwise.
 
 1.  Install prerequisites + pipenv as mentioned in
-    [Bare metal route](/setup#bare_metal).
+    [Bare metal route](setup.md#bare_metal).
 
 2.  Copy `paperless.conf.example` to `paperless.conf` and enable debug
     mode within the file via `PAPERLESS_DEBUG=true`.
@@ -81,10 +81,6 @@ first-time setup.
     !!! note
 
         Using a virtual environment is highly recommended. You can spawn one via `pipenv shell`.
-        Make sure you're using Python 3.10.x or lower. Otherwise you might
-        get issues with building dependencies. You can use
-        [pyenv](https://github.com/pyenv/pyenv) to install a specific
-        Python version.
 
 5.  Install pre-commit hooks:
 
@@ -103,17 +99,17 @@ first-time setup.
 
 7.  You can now either ...
 
-    - install redis or
+    -   install redis or
 
-    - use the included `scripts/start_services.sh` to use docker to fire
-      up a redis instance (and some other services such as tika,
-      gotenberg and a database server) or
+    -   use the included `scripts/start_services.sh` to use docker to fire
+        up a redis instance (and some other services such as tika,
+        gotenberg and a database server) or
 
-    - spin up a bare redis container
+    -   spin up a bare redis container
 
-      ```
-      $ docker run -d -p 6379:6379 --restart unless-stopped redis:latest
-      ```
+        ```
+        $ docker run -d -p 6379:6379 --restart unless-stopped redis:latest
+        ```
 
 8.  Continue with either back-end or front-end development – or both :-).
 
@@ -126,9 +122,9 @@ work well for development, but you can use whatever you want.
 Configure the IDE to use the `src/`-folder as the base source folder.
 Configure the following launch configurations in your IDE:
 
-- `python3 manage.py runserver`
-- `python3 manage.py document_consumer`
-- `celery --app paperless worker -l DEBUG` (or any other log level)
+-   `python3 manage.py runserver`
+-   `python3 manage.py document_consumer`
+-   `celery --app paperless worker -l DEBUG` (or any other log level)
 
 To start them all:
 
@@ -154,11 +150,11 @@ $ ng build --configuration production
 
 ### Testing
 
-- Run `pytest` in the `src/` directory to execute all tests. This also
-  generates a HTML coverage report. When runnings test, `paperless.conf`
-  is loaded as well. However, the tests rely on the default
-  configuration. This is not ideal. But for now, make sure no settings
-  except for DEBUG are overridden when testing.
+-   Run `pytest` in the `src/` directory to execute all tests. This also
+    generates a HTML coverage report. When runnings test, `paperless.conf`
+    is loaded as well. However, the tests rely on the default
+    configuration. This is not ideal. But for now, make sure no settings
+    except for DEBUG are overridden when testing.
 
 !!! note
 
@@ -177,68 +173,69 @@ The front end is built using AngularJS. In order to get started, you need Node.j
 
     The following commands are all performed in the `src-ui`-directory. You will need a running back end (including an active session) to connect to the back end API. To spin it up refer to the commands under the section [above](#back-end-development).
 
-1. Install the Angular CLI. You might need sudo privileges
-   to perform this command:
+1.  Install the Angular CLI. You might need sudo privileges to perform this command:
 
-   ```bash
-   $ npm install -g @angular/cli
-   ```
+    ```bash
+    $ npm install -g @angular/cli
+    ```
 
-2. Make sure that it's on your path.
+2.  Make sure that it's on your path.
 
-3. Install all necessary modules:
+3.  Install all necessary modules:
 
-   ```bash
-   $ npm install
-   ```
+    ```bash
+    $ npm install
+    ```
 
-4. You can launch a development server by running:
+4.  You can launch a development server by running:
 
-   ```bash
-   $ ng serve
-   ```
+    ```bash
+    $ ng serve
+    ```
 
-   This will automatically update whenever you save. However, in-place
-   compilation might fail on syntax errors, in which case you need to
-   restart it.
+    This will automatically update whenever you save. However, in-place
+    compilation might fail on syntax errors, in which case you need to
+    restart it.
 
-   By default, the development server is available on `http://localhost:4200/` and is configured to access the API at
-   `http://localhost:8000/api/`, which is the default of the backend. If you enabled `DEBUG` on the back end, several security overrides for allowed hosts, CORS and X-Frame-Options are in place so that the front end behaves exactly as in production.
+    By default, the development server is available on `http://localhost:4200/` and is configured to access the API at
+    `http://localhost:8000/api/`, which is the default of the backend. If you enabled `DEBUG` on the back end, several security overrides for allowed hosts, CORS and X-Frame-Options are in place so that the front end behaves exactly as in production.
 
 ### Testing and code style
 
-- The front end code (.ts, .html, .scss) use `prettier` for code
-  formatting via the Git `pre-commit` hooks which run automatically on
-  commit. See [above](#code-formatting-with-pre-commit-hooks) for installation instructions. You can also run this via the CLI with a
-  command such as
+The front end code (.ts, .html, .scss) use `prettier` for code
+formatting via the Git `pre-commit` hooks which run automatically on
+commit. See [above](#code-formatting-with-pre-commit-hooks) for installation instructions. You can also run this via the CLI with a
+command such as
 
-  ```bash
-  $ git ls-files -- '*.ts' | xargs pre-commit run prettier --files
-  ```
+```bash
+$ git ls-files -- '*.ts' | xargs pre-commit run prettier --files
+```
 
-- Front end testing uses Jest and Playwright. Unit tests and e2e tests,
-  respectively, can be run non-interactively with:
+Front end testing uses Jest and Playwright. Unit tests and e2e tests,
+respectively, can be run non-interactively with:
 
-  ```bash
-  $ ng test
-  $ npx playwright test
-  ```
+```bash
+$ ng test
+$ npx playwright test
+```
 
-  - Playwright also includes a UI which can be run with:
+Playwright also includes a UI which can be run with:
 
-    ```bash
-    $ npx playwright test --ui
-    ```
+```bash
+$ npx playwright test --ui
+```
 
-- In order to build the front end and serve it as part of Django, execute:
+### Building the frontend
 
-  ```bash
-  $ ng build --configuration production
-  ```
+In order to build the front end and serve it as part of Django, execute:
 
-  This will build the front end and put it in a location from which the
-  Django server will serve it as static content. This way, you can verify
-  that authentication is working.
+```bash
+$ ng build --configuration production
+```
+
+This will build the front end and put it in a location from which the
+Django server will serve it as static content. This way, you can verify
+that authentication is working.
 
 ## Localization
 
@@ -248,14 +245,14 @@ these parts have to be translated separately.
 
 ### Front end localization
 
-- The AngularJS front end does localization according to the [Angular
-  documentation](https://angular.io/guide/i18n).
-- The source language of the project is "en_US".
-- The source strings end up in the file `src-ui/messages.xlf`.
-- The translated strings need to be placed in the
-  `src-ui/src/locale/` folder.
-- In order to extract added or changed strings from the source files,
-  call `ng extract-i18n`.
+-   The AngularJS front end does localization according to the [Angular
+    documentation](https://angular.io/guide/i18n).
+-   The source language of the project is "en_US".
+-   The source strings end up in the file `src-ui/messages.xlf`.
+-   The translated strings need to be placed in the
+    `src-ui/src/locale/` folder.
+-   In order to extract added or changed strings from the source files,
+    call `ng extract-i18n`.
 
 Adding new languages requires adding the translated files in the
 `src-ui/src/locale/` folder and adjusting a couple files.
@@ -276,27 +273,17 @@ Adding new languages requires adding the translated files in the
     }
     ```
 
-2.  Add the language to the available options in
+2.  Add the language to the `LANGUAGE_OPTIONS` array in
     `src-ui/src/app/services/settings.service.ts`:
 
-    ```typescript
-    getLanguageOptions(): LanguageOption[] {
-        return [
-            {code: "en-us", name: $localize`English (US)`, englishName: "English (US)", dateInputFormat: "mm/dd/yyyy"},
-            {code: "en-gb", name: $localize`English (GB)`, englishName: "English (GB)", dateInputFormat: "dd/mm/yyyy"},
-            {code: "de", name: $localize`German`, englishName: "German", dateInputFormat: "dd.mm.yyyy"},
-            {code: "nl", name: $localize`Dutch`, englishName: "Dutch", dateInputFormat: "dd-mm-yyyy"},
-            {code: "fr", name: $localize`French`, englishName: "French", dateInputFormat: "dd/mm/yyyy"},
-            {code: "pt-br", name: $localize`Portuguese (Brazil)`, englishName: "Portuguese (Brazil)", dateInputFormat: "dd/mm/yyyy"}
-            // Add your new language here
-        ]
-    }
     ```
 
     `dateInputFormat` is a special string that defines the behavior of
     the date input fields and absolutely needs to contain "dd", "mm"
     and "yyyy".
 
+    ```
+
 3.  Import and register the Angular data for this locale in
     `src-ui/src/app/app.module.ts`:
 
@@ -311,18 +298,18 @@ A majority of the strings that appear in the back end appear only when
 the admin is used. However, some of these are still shown on the front
 end (such as error messages).
 
-- The django application does localization according to the [Django
-  documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
-- The source language of the project is "en_US".
-- Localization files end up in the folder `src/locale/`.
-- In order to extract strings from the application, call
-  `python3 manage.py makemessages -l en_US`. This is important after
-  making changes to translatable strings.
-- The message files need to be compiled for them to show up in the
-  application. Call `python3 manage.py compilemessages` to do this.
-  The generated files don't get committed into git, since these are
-  derived artifacts. The build pipeline takes care of executing this
-  command.
+-   The django application does localization according to the [Django
+    documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
+-   The source language of the project is "en_US".
+-   Localization files end up in the folder `src/locale/`.
+-   In order to extract strings from the application, call
+    `python3 manage.py makemessages -l en_US`. This is important after
+    making changes to translatable strings.
+-   The message files need to be compiled for them to show up in the
+    application. Call `python3 manage.py compilemessages` to do this.
+    The generated files don't get committed into git, since these are
+    derived artifacts. The build pipeline takes care of executing this
+    command.
 
 Adding new languages requires adding the translated files in the
 `src/locale/`-folder and adjusting the file
@@ -373,10 +360,10 @@ If you want to build the documentation locally, this is how you do it:
 The docker image is primarily built by the GitHub actions workflow, but
 it can be faster when developing to build and tag an image locally.
 
-Building the image works as with any image:
+Make sure you have the `docker-buildx` package installed. Building the image works as with any image:
 
 ```
-docker build --file Dockerfile --tag paperless:local --progress simple .
+docker build --file Dockerfile --tag paperless:local .
 ```
 
 ## Extending Paperless-ngx
@@ -391,10 +378,10 @@ base code.
 Paperless-ngx uses parsers to add documents. A parser is
 responsible for:
 
-- Retrieving the content from the original
-- Creating a thumbnail
-- _optional:_ Retrieving a created date from the original
-- _optional:_ Creating an archived document from the original
+-   Retrieving the content from the original
+-   Creating a thumbnail
+-   _optional:_ Retrieving a created date from the original
+-   _optional:_ Creating an archived document from the original
 
 Custom parsers can be added to Paperless-ngx to support more file types. In
 order to do that, you need to write the parser itself and announce its
@@ -452,14 +439,14 @@ def myparser_consumer_declaration(sender, **kwargs):
     }
 ```
 
-- `parser` is a reference to a class that extends `DocumentParser`.
-- `weight` is used whenever two or more parsers are able to parse a
-  file: The parser with the higher weight wins. This can be used to
-  override the parsers provided by Paperless-ngx.
-- `mime_types` is a dictionary. The keys are the mime types your
-  parser supports and the value is the default file extension that
-  Paperless-ngx should use when storing files and serving them for
-  download. We could guess that from the file extensions, but some
-  mime types have many extensions associated with them and the Python
-  methods responsible for guessing the extension do not always return
-  the same value.
+-   `parser` is a reference to a class that extends `DocumentParser`.
+-   `weight` is used whenever two or more parsers are able to parse a
+    file: The parser with the higher weight wins. This can be used to
+    override the parsers provided by Paperless-ngx.
+-   `mime_types` is a dictionary. The keys are the mime types your
+    parser supports and the value is the default file extension that
+    Paperless-ngx should use when storing files and serving them for
+    download. We could guess that from the file extensions, but some
+    mime types have many extensions associated with them and the Python
+    methods responsible for guessing the extension do not always return
+    the same value.

docs/faq.md

@@ -3,15 +3,16 @@
 ## _What's the general plan for Paperless-ngx?_
 
 **A:** While Paperless-ngx is already considered largely
-"feature-complete" it is a community-driven project and development
-will be guided in this way. New features can be submitted via GitHub
-discussions and "up-voted" by the community but this is not a
-guarantee the feature will be implemented. This project will always be
+"feature-complete", it is a community-driven project and development
+will be guided in this way. New features can be submitted via
+[GitHub discussions](https://github.com/paperless-ngx/paperless-ngx/discussions)
+and "up-voted" by the community, but this is not a
+guarantee that the feature will be implemented. This project will always be
 open to collaboration in the form of PRs, ideas etc.
 
 ## _I'm using docker. Where are my documents?_
 
-**A:** Your documents are stored inside the docker volume
+**A:** By default, your documents are stored inside the docker volume
 `paperless_media`. Docker manages this volume automatically for you. It
 is a persistent storage and will persist as long as you don't
 explicitly delete it. The actual location depends on your host operating
@@ -39,28 +40,28 @@ system. On Linux, chances are high that this location is
 You can always drag those files out of that folder to use them
 elsewhere. Here are a couple notes about that.
 
-- Paperless-ngx never modifies your original documents. It keeps
-  checksums of all documents and uses a scheduled sanity checker to
-  check that they remain the same.
-- By default, paperless uses the internal ID of each document as its
-  filename. This might not be very convenient for export. However, you
-  can adjust the way files are stored in paperless by
-  [configuring the filename format](/advanced_usage#file-name-handling).
-- [The exporter](/administration#exporter) is
-  another easy way to get your files out of paperless with reasonable
-  file names.
+-   Paperless-ngx never modifies your original documents. It keeps
+    checksums of all documents and uses a scheduled sanity checker to
+    check that they remain the same.
+-   By default, paperless uses the internal ID of each document as its
+    filename. This might not be very convenient for export. However, you
+    can adjust the way files are stored in paperless by
+    [configuring the filename format](advanced_usage.md#file-name-handling).
+-   [The exporter](administration.md#exporter) is
+    another easy way to get your files out of paperless with reasonable
+    file names.
 
 ## _What file types does paperless-ngx support?_
 
 **A:** Currently, the following files are supported:
 
-- PDF documents, PNG images, JPEG images, TIFF images, GIF images and
-  WebP images are processed with OCR and converted into PDF documents.
-- Plain text documents are supported as well and are added verbatim to
-  paperless.
-- With the optional Tika integration enabled (see [Tika configuration](/configuration#tika),
-  Paperless also supports various Office documents (.docx, .doc, odt,
-  .ppt, .pptx, .odp, .xls, .xlsx, .ods).
+-   PDF documents, PNG images, JPEG images, TIFF images, GIF images and
+    WebP images are processed with OCR and converted into PDF documents.
+-   Plain text documents are supported as well and are added verbatim to
+    paperless.
+-   With the optional Tika integration enabled (see [Tika configuration](https://docs.paperless-ngx.com/configuration#tika)),
+    Paperless also supports various Office documents (.docx, .doc, odt,
+    .ppt, .pptx, .odp, .xls, .xlsx, .ods).
 
 Paperless-ngx determines the type of a file by inspecting its content.
 The file extensions do not matter.
@@ -77,20 +78,27 @@ has to do much less work to serve the data.
 !!! note
 
     You can adjust some of the settings so that paperless uses less
-    processing power. See [setup](/setup#less-powerful-devices) for details.
+    processing power. See [setup](setup.md#less-powerful-devices) for details.
 
 ## _How do I install paperless-ngx on Raspberry Pi?_
 
-**A:** Docker images are available for armv7 and arm64 hardware, so just
-follow the docker-compose instructions. Apart from more required disk
+**A:** Docker images are available for arm64 hardware, so just
+follow the [Docker Compose instructions](https://docs.paperless-ngx.com/setup/#installation). Apart from more required disk
 space compared to a bare metal installation, docker comes with close to
 zero overhead, even on Raspberry Pi.
 
-If you decide to got with the bare metal route, be aware that some of
+If you decide to go with the bare metal route, be aware that some of
 the python requirements do not have precompiled packages for ARM /
 ARM64. Installation of these will require additional development
 libraries and compilation will take a long time.
 
+!!! note
+
+    For ARMv7 (32-bit) systems, paperless may still function, but it could require
+    modifications to the Dockerfile (if using Docker) or additional
+    tools for installing bare metal.  It is suggested to upgrade to arm64
+    instead.
+
 ## _How do I run this on Unraid?_
 
 **A:** Paperless-ngx is available as [community
@@ -102,10 +110,7 @@ Fahrer](https://github.com/Tooa) created a container template for that.
 **A:** I honestly don't know! As for all other devices that might be
 able to run paperless, you're a bit on your own. If you can't run the
 docker image, the documentation has instructions for bare metal
-installs. I'm running paperless on an i3 processor from 2015 or so.
-This is also what I use to test new releases with. Apart from that, I
-also have a Raspberry Pi, which I occasionally build the image on and
-see if it works.
+installs.
 
 ## _How do I proxy this with NGINX?_
 
@@ -122,8 +127,16 @@ ASGI-enabled web server as well that processes WebSocket connections,
 and configure Apache to redirect WebSocket connections to this server.
 Multiple options for ASGI servers exist:
 
-- `gunicorn` with `uvicorn` as the worker implementation (the default
-  of paperless)
-- `daphne` as a standalone server, which is the reference
-  implementation for ASGI.
-- `uvicorn` as a standalone server
+-   `gunicorn` with `uvicorn` as the worker implementation (the default
+    of paperless)
+-   `daphne` as a standalone server, which is the reference
+    implementation for ASGI.
+-   `uvicorn` as a standalone server
+
+## _What about the Redis licensing change and using one of the open source forks_?
+
+Currently (October 2024), forks of Redis such as Valkey or Redirect are not officially supported by our upstream
+libraries, so using one of these to replace Redis is not officially supported.
+
+However, they do claim to be compatible with the Redis protocol and will likely work, but we will
+not be updating from using Redis as the broker officially just yet.

docs/index.md

@@ -5,9 +5,16 @@
 **Paperless-ngx** is a _community-supported_ open-source document management system that transforms your
 physical documents into a searchable online archive so you can keep, well, _less paper_.
 
-[Get started](/setup){ .md-button .md-button--primary .index-callout }
+[Get started](setup.md){ .md-button .md-button--primary .index-callout }
 [Demo](https://demo.paperless-ngx.com){ .md-button .md-button--secondary target=\_blank }
 
+<div style="display: flex; justify-content: end; margin-top: -1.5rem;">
+  <a href="https://m.do.co/c/8d70b916d462" target="_blank">
+    <img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/PoweredByDO/DO_Powered_by_Badge_white.svg#only-dark" class="no-lightbox" width="150px">
+    <img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/PoweredByDO/DO_Powered_by_Badge_black.svg#only-light" class="no-lightbox" width="150px">
+  </a>
+</div>
+
 </div>
 <div class="grid-right" markdown>
 ![image](assets/screenshots/documents-smallcards.png#only-light){.index-screenshot}
@@ -15,103 +22,162 @@ physical documents into a searchable online archive so you can keep, well, _less
 </div>
 <div class="clear"></div>
 
-## Why This Exists
+## Features
 
-Paper is a nightmare. Environmental issues aside, there's no excuse for
-it in the 21st century. It takes up space, collects dust, doesn't
-support any form of a search feature, indexing is tedious, it's heavy
-and prone to damage & loss.
+-   **Organize and index** your scanned documents with tags, correspondents, types, and more.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
+-   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
+-   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+-   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
+-   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
+-   Supports PDF documents, images, plain text files, Office documents (Word, Excel, Powerpoint, and LibreOffice equivalents)[^1] and more.
+-   Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
+-   **Beautiful, modern web application** that features:
+    -   Customizable dashboard with statistics.
+    -   Filtering by tags, correspondents, types, and more.
+    -   Bulk editing of tags, correspondents, types and more.
+    -   Drag-and-drop uploading of documents throughout the app.
+    -   Customizable views can be saved and displayed on the dashboard and / or sidebar.
+    -   Support for custom fields of various data types.
+    -   Shareable public links with optional expiration.
+-   **Full text search** helps you find what you need:
+    -   Auto completion suggests relevant words from your documents.
+    -   Results are sorted by relevance to your search query.
+    -   Highlighting shows you which parts of the document matched the query.
+    -   Searching for similar documents ("More like this")
+-   **Email processing**[^1]: import documents from your email accounts:
+    -   Configure multiple accounts and rules for each account.
+    -   After processing, paperless can perform actions on the messages such as marking as read, deleting and more.
+-   A built-in robust **multi-user permissions** system that supports 'global' permissions as well as per document or object.
+-   A powerful workflow system that gives you even more control.
+-   **Optimized** for multi core systems: Paperless-ngx consumes multiple documents in parallel.
+-   The integrated sanity checker makes sure that your document archive is in good health.
 
-This software is designed to make "going paperless" easier. No more worrying
-about finding stuff again, feed documents right from the post box into
-the scanner and then shred them. Perhaps you might find it useful too.
+[^1]: Office document and email consumption support is optional and provided by Apache Tika (see [configuration](https://docs.paperless-ngx.com/configuration/#tika))
 
 ## Paperless, a history
 
-Paperless is a simple Django application running in two parts: a
-_Consumer_ (the thing that does the indexing) and the _Web server_ (the
-part that lets you search & download already-indexed documents). If you
-want to learn more about its functions keep on reading after the
-installation section.
+Paperless-ngx is the official successor to the original [Paperless](https://github.com/the-paperless-project/paperless) & [Paperless-ng](https://github.com/jonaswinkler/paperless-ng) projects and is designed to distribute the responsibility of advancing and supporting the project among a team of people. [Consider joining us!](https://github.com/paperless-ngx/paperless-ngx#community-support)
 
-Paperless-ngx is a document management system that transforms your
-physical documents into a searchable online archive so you can keep,
-well, _less paper_.
-
-Paperless-ngx forked from paperless-ng to continue the great work and
-distribute responsibility of supporting and advancing the project among
-a team of people.
-
-NG stands for both Angular (the framework used for the Frontend) and
-next-gen. Publishing this project under a different name also avoids
-confusion between paperless and paperless-ngx.
-
-If you want to learn about what's different in paperless-ngx from
-Paperless, check out these resources in the documentation:
-
-- [Some screenshots](#screenshots) of the new UI are available.
-- Read [this section](/advanced_usage#automatic-matching) if you want to learn about how paperless automates all
-  tagging using machine learning.
-- Paperless now comes with a [proper email consumer](/usage#usage-email) that's fully tested and production ready.
-- Paperless creates searchable PDF/A documents from whatever you put into the consumption directory. This means
-  that you can select text in image-only documents coming from your scanner.
-- See [this note](/administration#encryption) about GnuPG encryption in paperless-ngx.
-- Paperless is now integrated with a
-  [task processing queue](/setup#task_processor) that tells you at a glance when and why something is not working.
-- The [changelog](/changelog) contains a detailed list of all changes in paperless-ngx.
+Further discussion of the transition between these projects can be found at
+[ng#1599](https://github.com/jonaswinkler/paperless-ng/issues/1599) and [ng#1632](https://github.com/jonaswinkler/paperless-ng/issues/1632).
 
 ## Screenshots
 
-This is what Paperless-ngx looks like.
+Paperless-ngx aims to be as nice to use as it is useful. Check out some screenshots below.
 
-The dashboard shows customizable views on your document and allows
-document uploads:
+<div class="grid-flipped-left" markdown>
+  ![image](assets/screenshots/dashboard.png)
+</div>
+<div class="grid-flipped-right" markdown>
+  The dashboard shows saved views which can be sorted. Documents can be uploaded with the button or dropped anywhere in the application.
+</div>
+<div class="clear"></div>
 
-[![image](assets/screenshots/dashboard.png)](assets/screenshots/dashboard.png)
+The document list provides three different styles to browse your documents.
 
-The document list provides three different styles to scroll through your
-documents:
+![image](assets/screenshots/documents-table.png){: style="width:32%"}
+![image](assets/screenshots/documents-smallcards.png){: style="width:32%"}
+![image](assets/screenshots/documents-largecards.png){: style="width:32%"}
 
-[![image](assets/screenshots/documents-table.png)](assets/screenshots/documents-table.png)
+<div class="clear"></div>
 
-[![image](assets/screenshots/documents-smallcards.png)](assets/screenshots/documents-smallcards.png)
+<div class="grid-left" markdown>
+  Use the 'slim' sidebar to focus on your docs and minimize the UI.
+</div>
+<div class="grid-right" markdown>
+  ![image](assets/screenshots/documents-smallcards-slimsidebar.png)
+</div>
+<div class="clear"></div>
 
-[![image](assets/screenshots/documents-largecards.png)](assets/screenshots/documents-largecards.png)
+Of course, Paperless-ngx also supports dark mode:
 
-Paperless-ngx also supports dark mode:
+![image](assets/screenshots/documents-smallcards-dark.png)
 
-[![image](assets/screenshots/documents-smallcards-dark.png)](assets/screenshots/documents-smallcards-dark.png)
+<div class="clear"></div>
 
-Extensive filtering mechanisms:
+<div class="grid-left" markdown>
+  Quickly find documents with extensive filtering mechanisms.
+</div>
+<div class="grid-right" markdown>
+  ![image](assets/screenshots/documents-filter.png)
+</div>
+<div class="clear"></div>
+<div class="grid-left" markdown>
+  And perform bulk edit operations to set tags, correspondents, etc. as well as permissions.
+</div>
+<div class="grid-right" markdown>
+  ![image](assets/screenshots/bulk-edit.png)
+</div>
+<div class="clear"></div>
 
-[![image](assets/screenshots/documents-filter.png)](assets/screenshots/documents-filter.png)
+Side-by-side editing of documents.
 
-Bulk editing of document tags, correspondents, etc.:
+![image](assets/screenshots/editing.png)
 
-[![image](assets/screenshots/bulk-edit.png)](assets/screenshots/bulk-edit.png)
+<div class="grid-left" markdown>
+  Support for custom fields.
 
-Side-by-side editing of documents:
+![image](assets/screenshots/custom_field1.png)
 
-[![image](assets/screenshots/editing.png)](assets/screenshots/editing.png)
+</div>
+<div class="grid-right" markdown>
+  ![image](assets/screenshots/custom_field2.png)
+</div>
+<div class="clear"></div>
 
-Tag editing. This looks about the same for correspondents and document
-types.
+<div class="grid-left" markdown>
+  A robust permissions system with support for 'global' and document / object permissions.
 
-[![image](assets/screenshots/new-tag.png)](assets/screenshots/new-tag.png)
+![image](assets/screenshots/permissions_global.png)
 
-Searching provides auto complete and highlights the results.
+</div>
+<div class="grid-right" markdown>
+  ![image](assets/screenshots/permissions_document.png)
+</div>
+<div class="clear"></div>
 
-[![image](assets/screenshots/search-preview.png)](assets/screenshots/search-preview.png)
+<div class="grid-left" markdown>
+  Searching provides auto complete and highlights the results.
 
-[![image](assets/screenshots/search-results.png)](assets/screenshots/search-results.png)
+![image](assets/screenshots/search-preview.png)
 
-Fancy mail filters!
+</div>
+<div class="grid-right" markdown>
+  ![image](assets/screenshots/search-results.png)
+</div>
+<div class="clear"></div>
 
-[![image](assets/screenshots/mail-rules-edited.png)](assets/screenshots/mail-rules-edited.png)
+Tag, correspondent, document type and storage path editing.
+
+![image](assets/screenshots/new-tag.png){: style="width:21%; float: left"}
+![image](assets/screenshots/new-correspondent.png){: style="width:21%; margin-left: 4%; float: left"}
+![image](assets/screenshots/new-document_type.png){: style="width:21%; margin-left: 4%; float: left"}
+![image](assets/screenshots/new-storage_path.png){: style="width:21%; margin-left: 4%; float: left"}
+
+<div class="clear"></div>
+
+<div class="grid-half-left" markdown>
+  Mail rules support various filters and actions for incoming e-mails.
+
+![image](assets/screenshots/mail-rules-edited.png)
+
+</div>
+<div class="grid-half-right" markdown>
+  Workflows provide finer control over the document pipeline and trigger actions.
+
+![image](assets/screenshots/workflow.png)
+
+</div>
+<div class="clear"></div>
+
+<div class="clear"></div>
 
 Mobile devices are supported.
 
-[![image](assets/screenshots/mobile.png)](assets/screenshots/mobile.png)
+![image](assets/screenshots/mobile1.png){: style="width:32%"}
+![image](assets/screenshots/mobile2.png){: style="width:32%"}
+![image](assets/screenshots/mobile3.png){: style="width:32%"}
 
 ## Support
 
@@ -131,7 +197,7 @@ People interested in continuing the work on paperless-ngx are encouraged to reac
 
 ### Translation
 
-Paperless-ngx is available in many languages that are coordinated on [Crowdin](https://crwd.in/paperless-ngx). If you want to help out by translating paperless-ngx into your language, please head over to https://crwd.in/paperless-ngx, and thank you!
+Paperless-ngx is available in many languages that are coordinated on [Crowdin](https://crwd.in/paperless-ngx). If you want to help out by translating paperless-ngx into your language, please head over to the [Paperless-ngx project at Crowdin](https://crwd.in/paperless-ngx), and thank you!
 
 ## Scanners & Software
 

docs/setup.md

@@ -2,10 +2,11 @@
 
 You can go multiple routes to setup and run Paperless:
 
-- [Use the easy install docker script](#docker_script)
-- [Pull the image from Docker Hub](#docker_hub)
-- [Build the Docker image yourself](#docker_build)
-- [Install Paperless directly on your system manually (bare metal)](#bare_metal)
+-   [Use the easy install docker script](#docker_script)
+-   [Pull the image from Docker Hub](#docker_hub)
+-   [Build the Docker image yourself](#docker_build)
+-   [Install Paperless directly on your system manually (bare metal)](#bare_metal)
+-   A user-maintained list of commercial hosting providers can be found [in the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects)
 
 The Docker routes are quick & easy. These are the recommended routes.
 This configures all the stuff from the above automatically so that it
@@ -25,12 +26,16 @@ necessary configuration files, pull the docker image, start paperless
 and create your user account. This script essentially performs all the
 steps described in [Docker setup](#docker_hub) automatically.
 
-1.  Make sure that docker and docker-compose are installed.
+1.  Make sure that Docker and Docker Compose are installed.
+
+    !!! tip
+
+        See the Docker installation instructions at https://docs.docker.com/engine/install/
 
 2.  Download and run the installation script:
 
     ```shell-session
-    $ bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
+    $ bash -c "$(curl --location --silent --show-error https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
     ```
 
     !!! note
@@ -62,19 +67,19 @@ steps described in [Docker setup](#docker_hub) automatically.
         For new installations, it is recommended to use PostgreSQL as the
         database backend.
 
-3.  Install [Docker](https://www.docker.com/) and
-    [docker-compose](https://docs.docker.com/compose/install/).
+3.  Install [Docker](https://docs.docker.com/engine/install/) and
+    [Docker Compose](https://docs.docker.com/compose/install/).
 
     !!! warning
 
         If you want to use the included `docker-compose.*.yml` file, you
-        need to have at least Docker version **17.09.0** and docker-compose
-        version **1.17.0**. To check do: `docker-compose -v` or `docker -v`
+        need to have at least Docker version **17.09.0** and Docker Compose
+        version **v2**. To check do: `docker compose version` or `docker -v`
 
         See the [Docker installation guide](https://docs.docker.com/engine/install/) on how to install the current
         version of Docker for your operating system or Linux distribution of
-        choice. To get the latest version of docker-compose, follow the
-        [docker-compose installation guide](https://docs.docker.com/compose/install/linux/) if your package repository
+        choice. To get the latest version of Docker Compose, follow the
+        [Docker Compose installation guide](https://docs.docker.com/compose/install/linux/) if your package repository
         doesn't include it.
 
 4.  Modify `docker-compose.yml` to your preferences. You may want to
@@ -92,7 +97,7 @@ steps described in [Docker setup](#docker_hub) automatically.
     - /home/jonaswinkler/paperless-inbox:/usr/src/paperless/consume
     ```
 
-    Don't change the part after the colon or paperless wont find your
+    Don't change the part after the colon or paperless won't find your
     documents.
 
     You may also need to change the default port that the webserver will
@@ -100,14 +105,14 @@ steps described in [Docker setup](#docker_hub) automatically.
 
     ```yaml
     ports:
-      - 8000:8000
+        - 8000:8000
     ```
 
     Replace the part BEFORE the colon with a port of your choice:
 
     ```yaml
     ports:
-      - 8010:8000
+        - 8010:8000
     ```
 
     Don't change the part after the colon or edit other lines that
@@ -117,14 +122,18 @@ steps described in [Docker setup](#docker_hub) automatically.
 
     **Rootless**
 
+    !!! warning
+
+        It is currently not possible to run the container rootless if additional languages are specified via `PAPERLESS_OCR_LANGUAGES`.
+
     If you want to run Paperless as a rootless container, you will need
     to do the following in your `docker-compose.yml`:
 
-    - set the `user` running the container to map to the `paperless`
-      user in the container. This value (`user_id` below), should be
-      the same id that `USERMAP_UID` and `USERMAP_GID` are set to in
-      the next step. See `USERMAP_UID` and `USERMAP_GID`
-      [here](/configuration#docker).
+    -   set the `user` running the container to map to the `paperless`
+        user in the container. This value (`user_id` below), should be
+        the same id that `USERMAP_UID` and `USERMAP_GID` are set to in
+        the next step. See `USERMAP_UID` and `USERMAP_GID`
+        [here](configuration.md#docker).
 
     Your entry for Paperless should contain something like:
 
@@ -148,12 +157,12 @@ steps described in [Docker setup](#docker_hub) automatically.
     !!! note
 
         You can copy any setting from the file `paperless.conf.example` and
-        paste it here. Have a look at [configuration](/configuration) to see what's available.
+        paste it here. Have a look at [configuration](configuration.md) to see what's available.
 
     !!! note
 
         You can utilize Docker secrets for configuration settings by
-        appending `_FILE` to configuration values. For example `PAPERLESS_DBUSER`
+        appending `_FILE` to configuration values. For example [`PAPERLESS_DBUSER`](configuration.md#PAPERLESS_DBUSER)
         can be set using `PAPERLESS_DBUSER_FILE=/var/run/secrets/password.txt`.
 
     !!! warning
@@ -162,16 +171,16 @@ steps described in [Docker setup](#docker_hub) automatically.
         system notifications with `inotify`. When storing the consumption
         directory on such a file system, paperless will not pick up new
         files with the default configuration. You will need to use
-        `PAPERLESS_CONSUMER_POLLING`, which will disable inotify. See
-        [here](/configuration#polling).
+        [`PAPERLESS_CONSUMER_POLLING`](configuration.md#PAPERLESS_CONSUMER_POLLING), which will disable inotify. See
+        [here](configuration.md#polling).
 
-6.  Run `docker-compose pull`. This will pull the image.
+6.  Run `docker compose pull`. This will pull the image.
 
 7.  To be able to login, you will need a super user. To create it,
     execute the following command:
 
     ```shell-session
-    $ docker-compose run --rm webserver createsuperuser
+    $ docker compose run --rm webserver createsuperuser
     ```
 
     or using docker exec from within the container:
@@ -183,7 +192,7 @@ steps described in [Docker setup](#docker_hub) automatically.
     This will prompt you to set a username, an optional e-mail address
     and finally a password (at least 8 characters).
 
-8.  Run `docker-compose up -d`. This will create and start the necessary containers.
+8.  Run `docker compose up -d`. This will create and start the necessary containers.
 
 9.  The default `docker-compose.yml` exports the webserver on your local
     port
@@ -209,39 +218,27 @@ steps described in [Docker setup](#docker_hub) automatically.
     root as well.
 
 3.  In the `docker-compose.yml` file, find the line that instructs
-    docker-compose to pull the paperless image from Docker Hub:
+    Docker Compose to pull the paperless image from Docker Hub:
 
     ```yaml
     webserver:
-      image: ghcr.io/paperless-ngx/paperless-ngx:latest
+        image: ghcr.io/paperless-ngx/paperless-ngx:latest
     ```
 
-    and replace it with a line that instructs docker-compose to build
+    and replace it with a line that instructs Docker Compose to build
     the image from the current working directory instead:
 
     ```yaml
     webserver:
-      build:
-        context: .
-        args:
-          QPDF_VERSION: x.y.x
-          PIKEPDF_VERSION: x.y.z
-          PSYCOPG2_VERSION: x.y.z
-          JBIG2ENC_VERSION: 0.29
+        build:
+            context: .
     ```
 
-    !!! note
-
-        You should match the build argument versions to the version for the
-        release you have checked out. These are pre-built images with
-        certain, more updated software. If you want to build these images
-        your self, that is possible, but beyond the scope of these steps.
-
 4.  Follow steps 3 to 8 of [Docker Setup](#docker_hub). When asked to run
-    `docker-compose pull` to pull the image, do
+    `docker compose pull` to pull the image, do
 
     ```shell-session
-    $ docker-compose build
+    $ docker compose build
     ```
 
     instead to build the image.
@@ -253,43 +250,48 @@ a minimal installation of Debian/Buster, which is the current stable
 release at the time of writing. Windows is not and will never be
 supported.
 
+Paperless requires Python 3. At this time, 3.10 - 3.12 are tested versions.
+Newer versions may work, but some dependencies may not fully support newer versions.
+Support for older Python versions may be dropped as they reach end of life or as newer versions
+are released, dependency support is confirmed, etc.
+
 1.  Install dependencies. Paperless requires the following packages.
 
-    - `python3` 3.8, 3.9
-    - `python3-pip`
-    - `python3-dev`
-    - `default-libmysqlclient-dev` for MariaDB
-    - `fonts-liberation` for generating thumbnails for plain text
-      files
-    - `imagemagick` >= 6 for PDF conversion
-    - `gnupg` for handling encrypted documents
-    - `libpq-dev` for PostgreSQL
-    - `libmagic-dev` for mime type detection
-    - `mariadb-client` for MariaDB compile time
-    - `mime-support` for mime type detection
-    - `libzbar0` for barcode detection
-    - `poppler-utils` for barcode detection
+    -   `python3`
+    -   `python3-pip`
+    -   `python3-dev`
+    -   `default-libmysqlclient-dev` for MariaDB
+    -   `pkg-config` for mysqlclient (python dependency)
+    -   `fonts-liberation` for generating thumbnails for plain text
+        files
+    -   `imagemagick` >= 6 for PDF conversion
+    -   `gnupg` for handling encrypted documents
+    -   `libpq-dev` for PostgreSQL
+    -   `libmagic-dev` for mime type detection
+    -   `mariadb-client` for MariaDB compile time
+    -   `libzbar0` for barcode detection
+    -   `poppler-utils` for barcode detection
 
     Use this list for your preferred package management:
 
     ```
-    python3 python3-pip python3-dev imagemagick fonts-liberation gnupg libpq-dev default-libmysqlclient-dev libmagic-dev mime-support libzbar0 poppler-utils
+    python3 python3-pip python3-dev imagemagick fonts-liberation gnupg libpq-dev default-libmysqlclient-dev pkg-config libmagic-dev libzbar0 poppler-utils
     ```
 
     These dependencies are required for OCRmyPDF, which is used for text
     recognition.
 
-    - `unpaper`
-    - `ghostscript`
-    - `icc-profiles-free`
-    - `qpdf`
-    - `liblept5`
-    - `libxml2`
-    - `pngquant` (suggested for certain PDF image optimizations)
-    - `zlib1g`
-    - `tesseract-ocr` >= 4.0.0 for OCR
-    - `tesseract-ocr` language packs (`tesseract-ocr-eng`,
-      `tesseract-ocr-deu`, etc)
+    -   `unpaper`
+    -   `ghostscript`
+    -   `icc-profiles-free`
+    -   `qpdf`
+    -   `liblept5`
+    -   `libxml2`
+    -   `pngquant` (suggested for certain PDF image optimizations)
+    -   `zlib1g`
+    -   `tesseract-ocr` >= 4.0.0 for OCR
+    -   `tesseract-ocr` language packs (`tesseract-ocr-eng`,
+        `tesseract-ocr-deu`, etc)
 
     Use this list for your preferred package management:
 
@@ -299,11 +301,21 @@ supported.
 
     On Raspberry Pi, these libraries are required as well:
 
-    - `libatlas-base-dev`
-    - `libxslt1-dev`
+    -   `libatlas-base-dev`
+    -   `libxslt1-dev`
+    -   `mime-support`
 
-    You will also need `build-essential`, `python3-setuptools` and
-    `python3-wheel` for installing some of the python dependencies.
+    You will also need these for installing some of the python dependencies:
+
+    -   `build-essential`
+    -   `python3-setuptools`
+    -   `python3-wheel`
+
+    Use this list for your preferred package management:
+
+    ```
+    build-essential python3-setuptools python3-wheel
+    ```
 
 2.  Install `redis` >= 6.0 and configure it to start automatically.
 
@@ -341,41 +353,41 @@ supported.
     home folder of the user you created before (`/opt/paperless`).
 
     Optional: If you cloned the git repo, you will have to
-    compile the frontend yourself, see [here](/development#front-end-development)
+    compile the frontend yourself, see [here](development.md#front-end-development)
     and use the `build` step, not `serve`.
 
-6.  Configure paperless. See [configuration](/configuration) for details.
+6.  Configure paperless. See [configuration](configuration.md) for details.
     Edit the included `paperless.conf` and adjust the settings to your
     needs. Required settings for getting
     paperless running are:
 
-    - `PAPERLESS_REDIS` should point to your redis server, such as
-      <redis://localhost:6379>.
-    - `PAPERLESS_DBENGINE` optional, and should be one of `postgres`,
-      `mariadb`, or `sqlite`
-    - `PAPERLESS_DBHOST` should be the hostname on which your
-      PostgreSQL server is running. Do not configure this to use
-      SQLite instead. Also configure port, database name, user and
-      password as necessary.
-    - `PAPERLESS_CONSUMPTION_DIR` should point to a folder which
-      paperless should watch for documents. You might want to have
-      this somewhere else. Likewise, `PAPERLESS_DATA_DIR` and
-      `PAPERLESS_MEDIA_ROOT` define where paperless stores its data.
-      If you like, you can point both to the same directory.
-    - `PAPERLESS_SECRET_KEY` should be a random sequence of
-      characters. It's used for authentication. Failure to do so
-      allows third parties to forge authentication credentials.
-    - `PAPERLESS_URL` if you are behind a reverse proxy. This should
-      point to your domain. Please see
-      [configuration](/configuration) for more
-      information.
+    -   [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your redis server, such as
+        <redis://localhost:6379>.
+    -   [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) optional, and should be one of `postgres`,
+        `mariadb`, or `sqlite`
+    -   [`PAPERLESS_DBHOST`](configuration.md#PAPERLESS_DBHOST) should be the hostname on which your
+        PostgreSQL server is running. Do not configure this to use
+        SQLite instead. Also configure port, database name, user and
+        password as necessary.
+    -   [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to a folder which
+        paperless should watch for documents. You might want to have
+        this somewhere else. Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
+        [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where paperless stores its data.
+        If you like, you can point both to the same directory.
+    -   [`PAPERLESS_SECRET_KEY`](configuration.md#PAPERLESS_SECRET_KEY) should be a random sequence of
+        characters. It's used for authentication. Failure to do so
+        allows third parties to forge authentication credentials.
+    -   [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
+        point to your domain. Please see
+        [configuration](configuration.md) for more
+        information.
 
     Many more adjustments can be made to paperless, especially the OCR
     part. The following options are recommended for everyone:
 
-    - Set `PAPERLESS_OCR_LANGUAGE` to the language most of your
-      documents are written in.
-    - Set `PAPERLESS_TIME_ZONE` to your local time zone.
+    -   Set [`PAPERLESS_OCR_LANGUAGE`](configuration.md#PAPERLESS_OCR_LANGUAGE) to the language most of your
+        documents are written in.
+    -   Set [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to your local time zone.
 
     !!! warning
 
@@ -383,9 +395,9 @@ supported.
 
 7.  Create the following directories if they are missing:
 
-    - `/opt/paperless/media`
-    - `/opt/paperless/data`
-    - `/opt/paperless/consume`
+    -   `/opt/paperless/media`
+    -   `/opt/paperless/data`
+    -   `/opt/paperless/consume`
 
     Adjust as necessary if you configured different folders.
     Ensure that the paperless user has write permissions for every one
@@ -403,8 +415,7 @@ supported.
     sudo chown paperless:paperless /opt/paperless/consume
     ```
 
-8.  Install python requirements from the `requirements.txt` file. It is
-    up to you if you wish to use a virtual environment or not. First you should update your pip, so it gets the actual packages.
+8.  Install python requirements from the `requirements.txt` file.
 
     ```shell-session
     sudo -Hu paperless pip3 install -r requirements.txt
@@ -413,6 +424,12 @@ supported.
     This will install all python dependencies in the home directory of
     the new paperless user.
 
+    !!! tip
+
+        It is up to you if you wish to use a virtual environment or not for the Python
+        dependencies.  This is an alternative to the above and may require adjusting
+        the example scripts to utilize the virtual environment paths
+
 9.  Go to `/opt/paperless/src`, and execute the following commands:
 
     ```bash
@@ -521,10 +538,9 @@ supported.
     not available for most distributions.
 
 15. Optional: If using the NLTK machine learning processing (see
-    `PAPERLESS_ENABLE_NLTK` in [configuration](/configuration#software_tweaks) for details),
+    [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) for details),
     download the NLTK data for the Snowball
-    Stemmer, Stopwords and Punkt tokenizer to your
-    `PAPERLESS_DATA_DIR/nltk`. Refer to the [NLTK
+    Stemmer, Stopwords and Punkt tokenizer to `/usr/share/nltk_data`. Refer to the [NLTK
     instructions](https://www.nltk.org/data.html) for details on how to
     download the data.
 
@@ -552,7 +568,7 @@ to
 image: ghcr.io/paperless-ngx/paperless-ngx:latest
 ```
 
-and then run `docker-compose up -d` which will pull the new image
+and then run `docker compose up -d` which will pull the new image
 recreate the container. That's it!
 
 Users who installed with the bare-metal route should also update their
@@ -570,21 +586,21 @@ your setup depending on how you installed paperless.
 This setup describes how to update an existing paperless Docker
 installation. The important things to keep in mind are as follows:
 
-- Read the [changelog](/changelog) and
-  take note of breaking changes.
-- You should decide if you want to stick with SQLite or want to
-  migrate your database to PostgreSQL. See [documentation](#sqlite_to_psql)
-  for details on
-  how to move your data from SQLite to PostgreSQL. Both work fine with
-  paperless. However, if you already have a database server running
-  for other services, you might as well use it for paperless as well.
-- The task scheduler of paperless, which is used to execute periodic
-  tasks such as email checking and maintenance, requires a
-  [redis](https://redis.io/) message broker instance. The
-  docker-compose route takes care of that.
-- The layout of the folder structure for your documents and data
-  remains the same, so you can just plug your old docker volumes into
-  paperless-ngx and expect it to find everything where it should be.
+-   Read the [changelog](changelog.md) and
+    take note of breaking changes.
+-   You should decide if you want to stick with SQLite or want to
+    migrate your database to PostgreSQL. See [documentation](#sqlite_to_psql)
+    for details on
+    how to move your data from SQLite to PostgreSQL. Both work fine with
+    paperless. However, if you already have a database server running
+    for other services, you might as well use it for paperless as well.
+-   The task scheduler of paperless, which is used to execute periodic
+    tasks such as email checking and maintenance, requires a
+    [redis](https://redis.io/) message broker instance. The
+    Docker Compose route takes care of that.
+-   The layout of the folder structure for your documents and data
+    remains the same, so you can just plug your old docker volumes into
+    paperless-ngx and expect it to find everything where it should be.
 
 Migration to paperless-ngx is then performed in a few simple steps:
 
@@ -592,7 +608,7 @@ Migration to paperless-ngx is then performed in a few simple steps:
 
     ```bash
     $ cd /path/to/current/paperless
-    $ docker-compose down
+    $ docker compose down
     ```
 
 2.  Do a backup for two purposes: If something goes wrong, you still
@@ -600,7 +616,7 @@ Migration to paperless-ngx is then performed in a few simple steps:
     switch back to paperless.
 
 3.  Download the latest release of paperless-ngx. You can either go with
-    the docker-compose files from
+    the Docker Compose files from
     [here](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose)
     or clone the repository to build the image yourself (see
     [above](#docker_build)). You can
@@ -630,14 +646,14 @@ Migration to paperless-ngx is then performed in a few simple steps:
     See [Docker setup](#docker_hub) details on
     which edits are advised.
 
-6.  [Update paperless.](/administration#updating)
+6.  [Update paperless.](administration.md#updating)
 
 7.  In order to find your existing documents with the new search
     feature, you need to invoke a one-time operation that will create
     the search index:
 
     ```shell-session
-    $ docker-compose run --rm webserver document_index reindex
+    $ docker compose run --rm webserver document_index reindex
     ```
 
     This will migrate your database and create the search index. After
@@ -646,7 +662,7 @@ Migration to paperless-ngx is then performed in a few simple steps:
 8.  Start paperless-ngx.
 
     ```bash
-    $ docker-compose up -d
+    $ docker compose up -d
     ```
 
     This will run paperless in the background and automatically start it
@@ -669,120 +685,46 @@ commands as well.
 1.  Stop and remove the paperless container
 2.  If using an external database, stop the container
 3.  Update Redis configuration
-    a) If `REDIS_URL` is already set, change it to `PAPERLESS_REDIS`
-    and continue to step 4.
-    b) Otherwise, in the `docker-compose.yml` add a new service for
-    Redis, following [the example compose
-    files](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose)
-    c) Set the environment variable `PAPERLESS_REDIS` so it points to
-    the new Redis container
+
+    1. If `REDIS_URL` is already set, change it to [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS)
+       and continue to step 4.
+
+    1. Otherwise, in the `docker-compose.yml` add a new service for
+       Redis, following [the example compose
+       files](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose)
+
+    1. Set the environment variable [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) so it points to
+       the new Redis container
+
 4.  Update user mapping
-    a) If set, change the environment variable `PUID` to `USERMAP_UID`
-    b) If set, change the environment variable `PGID` to `USERMAP_GID`
+
+    1. If set, change the environment variable `PUID` to `USERMAP_UID`
+
+    1. If set, change the environment variable `PGID` to `USERMAP_GID`
+
 5.  Update configuration paths
-    a) Set the environment variable `PAPERLESS_DATA_DIR` to `/config`
+
+    1. Set the environment variable [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) to `/config`
+
 6.  Update media paths
-    a) Set the environment variable `PAPERLESS_MEDIA_ROOT` to
-    `/data/media`
+
+    1. Set the environment variable [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) to
+       `/data/media`
+
 7.  Update timezone
-    a) Set the environment variable `PAPERLESS_TIME_ZONE` to the same
-    value as `TZ`
+
+    1. Set the environment variable [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to the same
+       value as `TZ`
+
 8.  Modify the `image:` to point to
     `ghcr.io/paperless-ngx/paperless-ngx:latest` or a specific version
     if preferred.
-9.  Start the containers as before, using `docker-compose`.
+9.  Start the containers as before, using `docker compose`.
 
 ## Moving data from SQLite to PostgreSQL or MySQL/MariaDB {#sqlite_to_psql}
 
-Moving your data from SQLite to PostgreSQL or MySQL/MariaDB is done via
-executing a series of django management commands as below. The commands
-below use PostgreSQL, but are applicable to MySQL/MariaDB with the
-
-!!! warning
-
-    Make sure that your SQLite database is migrated to the latest version.
-    Starting paperless will make sure that this is the case. If your try to
-    load data from an old database schema in SQLite into a newer database
-    schema in PostgreSQL, you will run into trouble.
-
-!!! warning
-
-    On some database fields, PostgreSQL enforces predefined limits on
-    maximum length, whereas SQLite does not. The fields in question are the
-    title of documents (128 characters), names of document types, tags and
-    correspondents (128 characters), and filenames (1024 characters). If you
-    have data in these fields that surpasses these limits, migration to
-    PostgreSQL is not possible and will fail with an error.
-
-!!! warning
-
-    MySQL is case insensitive by default, treating values like "Name" and
-    "NAME" as identical. See [MySQL caveats](/advanced_usage#mysql-caveats) for details.
-
-!!! warning
-
-    MySQL also enforces limits on maximum lengths, but does so differently than
-    PostgreSQL.  It may not be possible to migrate to MySQL due to this.
-
-!!! warning
-
-    Using mariadb version 10.4+ is recommended. Using the `utf8mb3` character set on
-    an older system may fix issues that can arise while setting up Paperless-ngx but
-    `utf8mb3` can cause issues with consumption (where `utf8mb4` does not).
-
-1.  Stop paperless, if it is running.
-
-2.  Tell paperless to use PostgreSQL:
-
-    a) With docker, copy the provided `docker-compose.postgres.yml`
-    file to `docker-compose.yml`. Remember to adjust the consumption
-    directory, if necessary.
-    b) Without docker, configure the database in your `paperless.conf`
-    file. See [configuration](/configuration) for
-    details.
-
-3.  Open a shell and initialize the database:
-
-    a) With docker, run the following command to open a shell within
-    the paperless container:
-
-        ``` shell-session
-        $ cd /path/to/paperless
-        $ docker-compose run --rm webserver /bin/bash
-        ```
-
-        This will launch the container and initialize the PostgreSQL
-        database.
-
-    b) Without docker, remember to activate any virtual environment,
-    switch to the `src` directory and create the database schema:
-
-        ``` shell-session
-        $ cd /path/to/paperless/src
-        $ python3 manage.py migrate
-        ```
-
-        This will not copy any data yet.
-
-4.  Dump your data from SQLite:
-
-    ```shell-session
-    $ python3 manage.py dumpdata --database=sqlite --exclude=contenttypes --exclude=auth.Permission > data.json
-    ```
-
-5.  Load your data into PostgreSQL:
-
-    ```shell-session
-    $ python3 manage.py loaddata data.json
-    ```
-
-6.  If operating inside Docker, you may exit the shell now.
-
-    ```shell-session
-    $ exit
-    ```
-
-7.  Start paperless.
+The best way to migrate between database types is to perform an [export](administration.md#exporter) and then
+[import](administration.md#importer) into a clean installation of Paperless-ngx.
 
 ## Moving back to Paperless
 
@@ -801,7 +743,7 @@ Execute this:
 
 ```shell-session
 $ cd /path/to/paperless
-$ docker-compose run --rm webserver migrate documents 0023
+$ docker compose run --rm webserver migrate documents 0023
 ```
 
 Or without docker:
@@ -821,37 +763,37 @@ Paperless runs on Raspberry Pi. However, some things are rather slow on
 the Pi and configuring some options in paperless can help improve
 performance immensely:
 
-- Stick with SQLite to save some resources.
-- Consider setting `PAPERLESS_OCR_PAGES` to 1, so that paperless will
-  only OCR the first page of your documents. In most cases, this page
-  contains enough information to be able to find it.
-- `PAPERLESS_TASK_WORKERS` and `PAPERLESS_THREADS_PER_WORKER` are
-  configured to use all cores. The Raspberry Pi models 3 and up have 4
-  cores, meaning that paperless will use 2 workers and 2 threads per
-  worker. This may result in sluggish response times during
-  consumption, so you might want to lower these settings (example: 2
-  workers and 1 thread to always have some computing power left for
-  other tasks).
-- Keep `PAPERLESS_OCR_MODE` at its default value `skip` and consider
-  OCR'ing your documents before feeding them into paperless. Some
-  scanners are able to do this!
-- Set `PAPERLESS_OCR_SKIP_ARCHIVE_FILE` to `with_text` to skip archive
-  file generation for already ocr'ed documents, or `always` to skip it
-  for all documents.
-- If you want to perform OCR on the device, consider using
-  `PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
-  less memory at the expense of slightly worse OCR results.
-- If using docker, consider setting `PAPERLESS_WEBSERVER_WORKERS` to 1. This will save some memory.
-- Consider setting `PAPERLESS_ENABLE_NLTK` to false, to disable the
-  more advanced language processing, which can take more memory and
-  processing time.
+-   Stick with SQLite to save some resources.
+-   Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that paperless will
+    only OCR the first page of your documents. In most cases, this page
+    contains enough information to be able to find it.
+-   [`PAPERLESS_TASK_WORKERS`](configuration.md#PAPERLESS_TASK_WORKERS) and [`PAPERLESS_THREADS_PER_WORKER`](configuration.md#PAPERLESS_THREADS_PER_WORKER) are
+    configured to use all cores. The Raspberry Pi models 3 and up have 4
+    cores, meaning that paperless will use 2 workers and 2 threads per
+    worker. This may result in sluggish response times during
+    consumption, so you might want to lower these settings (example: 2
+    workers and 1 thread to always have some computing power left for
+    other tasks).
+-   Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `skip` and consider
+    OCR'ing your documents before feeding them into paperless. Some
+    scanners are able to do this!
+-   Set [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE`](configuration.md#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) to `with_text` to skip archive
+    file generation for already ocr'ed documents, or `always` to skip it
+    for all documents.
+-   If you want to perform OCR on the device, consider using
+    `PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
+    less memory at the expense of slightly worse OCR results.
+-   If using docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
+-   Consider setting [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) to false, to disable the
+    more advanced language processing, which can take more memory and
+    processing time.
 
-For details, refer to [configuration](/configuration).
+For details, refer to [configuration](configuration.md).
 
 !!! note
 
     Updating the
-    [automatic matching algorithm](/advanced_usage#automatic-matching) takes quite a bit of time. However, the update mechanism
+    [automatic matching algorithm](advanced_usage.md#automatic-matching) takes quite a bit of time. However, the update mechanism
     checks if your data has changed before doing the heavy lifting. If you
     experience the algorithm taking too much cpu time, consider changing the
     schedule in the admin interface to daily. You can also manually invoke

docs/troubleshooting.md

@@ -4,27 +4,27 @@
 
 Check for the following issues:
 
-- Ensure that the directory you're putting your documents in is the
-  folder paperless is watching. With docker, this setting is performed
-  in the `docker-compose.yml` file. Without docker, look at the
-  `CONSUMPTION_DIR` setting. Don't adjust this setting if you're
-  using docker.
+-   Ensure that the directory you're putting your documents in is the
+    folder paperless is watching. With docker, this setting is performed
+    in the `docker-compose.yml` file. Without Docker, look at the
+    `CONSUMPTION_DIR` setting. Don't adjust this setting if you're
+    using docker.
 
-- Ensure that redis is up and running. Paperless does its task
-  processing asynchronously, and for documents to arrive at the task
-  processor, it needs redis to run.
+-   Ensure that redis is up and running. Paperless does its task
+    processing asynchronously, and for documents to arrive at the task
+    processor, it needs redis to run.
 
-- Ensure that the task processor is running. Docker does this
-  automatically. Manually invoke the task processor by executing
+-   Ensure that the task processor is running. Docker does this
+    automatically. Manually invoke the task processor by executing
 
-  ```shell-session
-  $ celery --app paperless worker
-  ```
+    ```shell-session
+    $ celery --app paperless worker
+    ```
 
-- Look at the output of paperless and inspect it for any errors.
+-   Look at the output of paperless and inspect it for any errors.
 
-- Go to the admin interface, and check if there are failed tasks. If
-  so, the tasks will contain an error message.
+-   Go to the admin interface, and check if there are failed tasks. If
+    so, the tasks will contain an error message.
 
 ## Consumer warns `OCR for XX failed`
 
@@ -46,8 +46,7 @@ run:
 If you notice that the consumer will only pickup files in the
 consumption directory at startup, but won't find any other files added
 later, you will need to enable filesystem polling with the configuration
-option `PAPERLESS_CONSUMER_POLLING`, see
-`[here](/configuration#polling).
+option [`PAPERLESS_CONSUMER_POLLING`](configuration.md#PAPERLESS_CONSUMER_POLLING).
 
 This will disable listening to filesystem changes with inotify and
 paperless will manually check the consumption directory for changes
@@ -79,12 +78,12 @@ Ensure that `chown` is possible on these directories.
 This indicates that the Auto matching algorithm found no documents to
 learn from. This may have two reasons:
 
-- You don't use the Auto matching algorithm: The error can be safely
-  ignored in this case.
-- You are using the Auto matching algorithm: The classifier explicitly
-  excludes documents with Inbox tags. Verify that there are documents
-  in your archive without inbox tags. The algorithm will only learn
-  from documents not in your inbox.
+-   You don't use the Auto matching algorithm: The error can be safely
+    ignored in this case.
+-   You are using the Auto matching algorithm: The classifier explicitly
+    excludes documents with Inbox tags. Verify that there are documents
+    in your archive without inbox tags. The algorithm will only learn
+    from documents not in your inbox.
 
 ## UserWarning in sklearn on every single document
 
@@ -121,17 +120,17 @@ Gotenberg raises this error.
 
 You can increase the timeout by configuring a command flag for Gotenberg
 (see also [here](https://gotenberg.dev/docs/modules/api#properties)). If
-using docker-compose, this is achieved by the following configuration
+using Docker Compose, this is achieved by the following configuration
 change in the `docker-compose.yml` file:
 
 ```yaml
 # The gotenberg chromium route is used to convert .eml files. We do not
 # want to allow external content like tracking pixels or even javascript.
 command:
-  - 'gotenberg'
-  - '--chromium-disable-javascript=true'
-  - '--chromium-allow-list=file:///tmp/.*'
-  - '--api-timeout=60'
+    - 'gotenberg'
+    - '--chromium-disable-javascript=true'
+    - '--chromium-allow-list=file:///tmp/.*'
+    - '--api-timeout=60'
 ```
 
 ## Permission denied errors in the consumption directory
@@ -139,13 +138,13 @@ command:
 You might encounter errors such as:
 
 ```shell-session
-The following error occured while consuming document.pdf: [Errno 13] Permission denied: '/usr/src/paperless/src/../consume/document.pdf'
+The following error occurred while consuming document.pdf: [Errno 13] Permission denied: '/usr/src/paperless/src/../consume/document.pdf'
 ```
 
 This happens when paperless does not have permission to delete files
 inside the consumption directory. Ensure that `USERMAP_UID` and
 `USERMAP_GID` are set to the user id and group id you use on the host
-operating system, if these are different from `1000`. See [Docker setup](/setup#docker_hub).
+operating system, if these are different from `1000`. See [Docker setup](setup.md#docker_hub).
 
 Also ensure that you are able to read and write to the consumption
 directory on the host.
@@ -265,8 +264,8 @@ This probably indicates paperless tried to consume the same file twice.
 This can happen for a number of reasons, depending on how documents are
 placed into the consume folder. If paperless is using inotify (the
 default) to check for documents, try adjusting the
-[inotify configuration](/configuration#inotify). If polling is enabled, try adjusting the
-[polling configuration](/configuration#polling).
+[inotify configuration](configuration.md#inotify). If polling is enabled, try adjusting the
+[polling configuration](configuration.md#polling).
 
 ## Consumer fails waiting for file to remain unmodified.
 
@@ -278,7 +277,7 @@ You might find messages like these in your log files:
 
 This indicates paperless timed out while waiting for the file to be
 completely written to the consume folder. Adjusting
-[polling configuration](/configuration#polling) values should resolve the issue.
+[polling configuration](configuration.md#polling) values should resolve the issue.
 
 !!! note
 
@@ -297,8 +296,8 @@ This indicates paperless was unable to open the file, as the OS reported
 the file as still being in use. To prevent a crash, paperless did not
 try to consume the file. If paperless is using inotify (the default) to
 check for documents, try adjusting the
-[inotify configuration](/configuration#inotify). If polling is enabled, try adjusting the
-[polling configuration](/configuration#polling).
+[inotify configuration](configuration.md#inotify). If polling is enabled, try adjusting the
+[polling configuration](configuration.md#polling).
 
 !!! note
 
@@ -320,7 +319,7 @@ many workers attempting to access the database simultaneously.
 
 Consider changing to the PostgreSQL database if you will be processing
 many documents at once often. Otherwise, try tweaking the
-`PAPERLESS_DB_TIMEOUT` setting to allow more time for the database to
+[`PAPERLESS_DB_TIMEOUT`](configuration.md#PAPERLESS_DB_TIMEOUT) setting to allow more time for the database to
 unlock. This may have minor performance implications.
 
 ## gunicorn fails to start with "is not a valid port number"
@@ -330,7 +329,7 @@ environment variable named `${serviceName}_PORT`. This is
 the same environment variable which is used by Paperless to optionally
 change the port gunicorn listens on.
 
-To fix this, set `PAPERLESS_PORT` again to your desired port, or the
+To fix this, set [`PAPERLESS_PORT`](configuration.md#PAPERLESS_PORT) again to your desired port, or the
 default of 8000.
 
 ## Database Warns about unique constraint "documents_tag_name_uniq
@@ -345,3 +344,29 @@ STATEMENT:  INSERT INTO "documents_tag" ("owner_id", "name", "match", "matching_
 
 This can happen during heavy consumption when using polling. Paperless will handle it correctly and the file
 will still be consumed
+
+## Consumption fails with "Ghostscript PDF/A rendering failed"
+
+Newer versions of OCRmyPDF will fail if it encounters errors during processing.
+This is intentional as the output archive file may differ in unexpected or undesired
+ways from the original. As the logs indicate, if you encounter this error you can set
+`PAPERLESS_OCR_USER_ARGS: '{"continue_on_soft_render_error": true}'` to try to 'force'
+processing documents with this issue.
+
+## Logs show "possible incompatible database column" when deleting documents {#convert-uuid-field}
+
+You may see errors when deleting documents like:
+
+```
+Data too long for column 'transaction_id' at row 1
+```
+
+This error can occur in installations which have upgraded from a version of Paperless-ngx that used Django 4 (Paperless-ngx versions prior to v2.13.0) with a MariaDB/MySQL database. Due to the backawards-incompatible change in Django 5, the column "documents_document.transaction_id" will need to be re-created, which can be done with a one-time run of the following management command:
+
+```shell-session
+$ python3 manage.py convert_mariadb_uuid
+```
+
+## Platform-Specific Deployment Troubleshooting
+
+A user-maintained wiki page is available to help troubleshoot issues that may arise when trying to deploy Paperless-ngx on specific platforms, for example SELinux. Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Platform%E2%80%90Specific-Troubleshooting).

docs/usage.md

@@ -10,37 +10,37 @@ and provides many utilities for finding and managing your documents.
 Paperless essentially consists of two different parts for managing your
 documents:
 
-- The _consumer_ watches a specified folder and adds all documents in
-  that folder to paperless.
-- The _web server_ provides a UI that you use to manage and search for
-  your scanned documents.
+-   The _consumer_ watches a specified folder and adds all documents in
+    that folder to paperless.
+-   The _web server_ provides a UI that you use to manage and search for
+    your scanned documents.
 
 Each document has a couple of fields that you can assign to them:
 
-- A _Document_ is a piece of paper that sometimes contains valuable
-  information.
-- The _correspondent_ of a document is the person, institution or
-  company that a document either originates from, or is sent to.
-- A _tag_ is a label that you can assign to documents. Think of labels
-  as more powerful folders: Multiple documents can be grouped together
-  with a single tag, however, a single document can also have multiple
-  tags. This is not possible with folders. The reason folders are not
-  implemented in paperless is simply that tags are much more versatile
-  than folders.
-- A _document type_ is used to demarcate the type of a document such
-  as letter, bank statement, invoice, contract, etc. It is used to
-  identify what a document is about.
-- The _date added_ of a document is the date the document was scanned
-  into paperless. You cannot and should not change this date.
-- The _date created_ of a document is the date the document was
-  initially issued. This can be the date you bought a product, the
-  date you signed a contract, or the date a letter was sent to you.
-- The _archive serial number_ (short: ASN) of a document is the
-  identifier of the document in your physical document binders. See
-  [recommended workflow](#usage-recommended-workflow) below.
-- The _content_ of a document is the text that was OCR'ed from the
-  document. This text is fed into the search engine and is used for
-  matching tags, correspondents and document types.
+-   A _Document_ is a piece of paper that sometimes contains valuable
+    information.
+-   The _correspondent_ of a document is the person, institution or
+    company that a document either originates from, or is sent to.
+-   A _tag_ is a label that you can assign to documents. Think of labels
+    as more powerful folders: Multiple documents can be grouped together
+    with a single tag, however, a single document can also have multiple
+    tags. This is not possible with folders. The reason folders are not
+    implemented in paperless is simply that tags are much more versatile
+    than folders.
+-   A _document type_ is used to demarcate the type of a document such
+    as letter, bank statement, invoice, contract, etc. It is used to
+    identify what a document is about.
+-   The _date added_ of a document is the date the document was scanned
+    into paperless. You cannot and should not change this date.
+-   The _date created_ of a document is the date the document was
+    initially issued. This can be the date you bought a product, the
+    date you signed a contract, or the date a letter was sent to you.
+-   The _archive serial number_ (short: ASN) of a document is the
+    identifier of the document in your physical document binders. See
+    [recommended workflow](#usage-recommended-workflow) below.
+-   The _content_ of a document is the text that was OCR'ed from the
+    document. This text is fed into the search engine and is used for
+    matching tags, correspondents and document types.
 
 ## Adding documents to paperless
 
@@ -62,7 +62,7 @@ following operations on your documents:
     paperless to create archived versions for digital documents, you can
     configure that by configuring
     `PAPERLESS_OCR_SKIP_ARCHIVE_FILE=with_text`. Please read the
-    [relevant section in the documentation](/configuration#ocr).
+    [relevant section in the documentation](configuration.md#ocr).
 
 !!! note
 
@@ -103,27 +103,16 @@ Typically, you're looking at an FTP server like
 
 ### Web UI Upload
 
-The dashboard has a file drop field to upload documents to paperless.
-Simply drag a file onto this field or select a file with the file
-dialog. Multiple files are supported.
-
-You can also upload documents on any other page of the web UI by
-dragging-and-dropping files into your browser window.
+The dashboard has a button to upload documents to paperless or you
+can simply drag a file anywhere into the app to initiate the consumption
+process.
 
 ### Mobile upload {#usage-mobile_upload}
 
-The mobile app over at [https://github.com/qcasey/paperless_share](https://github.com/qcasey/paperless_share)
-allows Android users to share any documents with paperless. This can be
-combined with any of the mobile scanning apps out there, such as Office
-Lens.
+Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects) for a user-maintained list of related projects and
+software (e.g. for mobile devices) that is compatible with Paperless-ngx.
 
-Furthermore, there is the [Paperless
-App](https://github.com/bauerj/paperless_app) as well, which not only
-has document upload, but also document browsing and download features.
-
-Another option is [Paperless Mobile](https://github.com/astubenbord/paperless-mobile), an Android app that supports document upload, scanning, management of labels and more.
-
-### IMAP (Email) {#usage-email}
+### Email {#usage-email}
 
 You can tell paperless-ngx to consume documents from your email
 accounts. This is a very flexible and powerful feature, if you regularly
@@ -145,28 +134,29 @@ These rules perform the following:
 5.  If documents were consumed from a mail, the rule action is performed
     on that mail.
 
-Paperless will completely ignore mails that do not match your filters.
-It will also only perform the action on mails that it has consumed
-documents from.
+Paperless will check all emails only once and completely ignore messages
+that do not match your filters. It will also only perform the rule action
+on e-mails that it has consumed documents from. The filename attachment
+patterns can include wildcards and multiple patterns separated by a comma.
 
 The actions all ensure that the same mail is not consumed twice by
 different means. These are as follows:
 
-- **Delete:** Immediately deletes mail that paperless has consumed
-  documents from. Use with caution.
-- **Mark as read:** Mark consumed mail as read. Paperless will not
-  consume documents from already read mails. If you read a mail before
-  paperless sees it, it will be ignored.
-- **Flag:** Sets the 'important' flag on mails with consumed
-  documents. Paperless will not consume flagged mails.
-- **Move to folder:** Moves consumed mails out of the way so that
-  paperless wont consume them again.
-- **Add custom Tag:** Adds a custom tag to mails with consumed
-  documents (the IMAP standard calls these "keywords"). Paperless
-  will not consume mails already tagged. Not all mail servers support
-  this feature!
+-   **Delete:** Immediately deletes mail that paperless has consumed
+    documents from. Use with caution.
+-   **Mark as read:** Mark consumed mail as read. Paperless will not
+    consume documents from already read mails. If you read a mail before
+    paperless sees it, it will be ignored.
+-   **Flag:** Sets the 'important' flag on mails with consumed
+    documents. Paperless will not consume flagged mails.
+-   **Move to folder:** Moves consumed mails out of the way so that
+    paperless won't consume them again.
+-   **Add custom Tag:** Adds a custom tag to mails with consumed
+    documents (the IMAP standard calls these "keywords"). Paperless
+    will not consume mails already tagged. Not all mail servers support
+    this feature!
 
-  - **Apple Mail support:** Apple Mail clients allow differently colored tags. For this to work use `apple:<color>` (e.g. _apple:green_) as a custom tag. Available colors are _red_, _orange_, _yellow_, _blue_, _green_, _violet_ and _grey_.
+    -   **Apple Mail support:** Apple Mail clients allow differently colored tags. For this to work use `apple:<color>` (e.g. _apple:green_) as a custom tag. Available colors are _red_, _orange_, _yellow_, _blue_, _green_, _violet_ and _grey_.
 
 !!! warning
 
@@ -208,48 +198,309 @@ different means. These are as follows:
     them further.
 
 Paperless is set up to check your mails every 10 minutes. This can be
-configured via `PAPERLESS_EMAIL_TASK_CRON` (see [software tweaks](/configuration#software_tweaks))
+configured via [`PAPERLESS_EMAIL_TASK_CRON`](configuration.md#PAPERLESS_EMAIL_TASK_CRON)
+
+#### OAuth Email Setup
+
+Paperless-ngx supports OAuth2 authentication for Gmail and Outlook email accounts. To set up an email account with OAuth2, you will need to create a 'developer' app with the respective provider and obtain the client ID and client secret and set the appropriate [configuration variables](configuration.md#email_oauth). You will also need to set either [`PAPERLESS_OAUTH_CALLBACK_BASE_URL`](configuration.md#PAPERLESS_OAUTH_CALLBACK_BASE_URL) or [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) to the correct value for the OAuth2 flow to work correctly.
+
+Specific instructions for setting up the required 'developer' app with Google or Microsoft are beyond the scope of this documentation, but you can find user-maintained instructions in [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Email-OAuth-App-Setup) or by searching the web.
+
+Once setup, navigating to the email settings page in Paperless-ngx will allow you to add an email account for Gmail or Outlook using OAuth2. After authenticating, you will be presented with the newly-created account where you will need to enter and save your email address. After this, the account will work as any other email account in Paperless-ngx and refreshing tokens will be handled automatically.
 
 ### REST API
 
-You can also submit a document using the REST API, see [POSTing documents](/api#file-uploads)
+You can also submit a document using the REST API, see [POSTing documents](api.md#file-uploads)
 for details.
 
 ## Permissions
 
-As of version 1.14.0 Paperless-ngx added core support for user / group permissions. Permissions is
-based around 'global' permissions as well as 'object-level' permissions. Global permissions designate
-which parts of the application a user can access (e.g. Documents, Tags, Settings) and object-level
-determine which objects are visible or editable. All objects have an 'owner' and 'view' and 'edit'
-permissions which can be granted to other users or groups.
+Permissions in Paperless-ngx are based around ['global' permissions](#global-permissions) as well as
+['object-level' permissions](#object-permissions). Global permissions determine which parts of the
+application a user can access (e.g. Documents, Tags, Settings) and object-level determine which
+objects are visible or editable. All objects have an 'owner' and 'view' and 'edit' permissions which
+can be granted to other users or groups. The paperless-ngx permissions system uses the built-in user
+model of the backend framework, Django.
 
-Permissions uses the built-in user model of the backend framework, Django.
+!!! tip
 
-!!! note
-
-    After migration to version 1.14.0 all existing documents, tags etc. will have no explicit owner
-    set which means they will be visible / editable by all users. Once an object has an owner set,
-    only the owner can explicitly grant / revoke permissions.
-
-!!! note
-
-    When first migrating to permissions it is recommended to use a 'superuser' account (which
-    would usually have been setup during installation) to ensure you have full permissions.
-
-    Note that superusers have access to all objects.
+    Object-level permissions only apply to the object itself. In other words, setting permissions
+    for a Tag will _not_ affect the permissions of documents that have the Tag.
 
 Permissions can be set using the new "Permissions" tab when editing documents, or bulk-applied
-in the UI by selecting documents and choosing the "Permissions" button. Owner can also optionally
-be set for documents uploaded via the API. Documents consumed via the consumption dir currently
-do not have an owner set.
+in the UI by selecting documents and choosing the "Permissions" button.
+
+### Default permissions
+
+[Workflows](#workflows) provide advanced ways to control permissions.
+
+For objects created via the web UI (tags, doc types, etc.) the default is to set the current user
+as owner and no extra permissions, but you can explicitly set these under Settings > Permissions.
+
+Documents consumed via the consumption directory do not have an owner or additional permissions set by default, but again, can be controlled with [Workflows](#workflows).
 
 ### Users and Groups
 
-Paperless-ngx versions after 1.14.0 allow creating and editing users and groups via the 'frontend' UI.
-These can be found under Settings > Users & Groups, assuming the user has access. If a user is designated
+Paperless-ngx supports editing users and groups via the 'frontend' UI, which can be found under
+Settings > Users & Groups, assuming the user has access. If a user is designated
 as a member of a group those permissions will be inherited and this is reflected in the UI. Explicit
 permissions can be granted to limit access to certain parts of the UI (and corresponding API endpoints).
 
+!!! tip
+
+    By default, new users are not granted any permissions, except those inherited from any group(s) of which they are a member.
+
+#### Superusers
+
+Superusers can access all parts of the front and backend application as well as any and all objects.
+
+#### Admin Status
+
+Admin status (Django 'staff status') grants access to viewing the paperless logs and the system status dialog
+as well as accessing the Django backend.
+
+#### Detailed Explanation of Global Permissions {#global-permissions}
+
+Global permissions define what areas of the app and API endpoints users can access. For example, they
+determine if a user can create, edit, delete or view _any_ documents, but individual documents themselves
+still have "object-level" permissions.
+
+| Type          | Details                                                                                                                                                                  |
+| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| AppConfig     | _Change_ or higher permissions grants access to the "Application Configuration" area.                                                                                    |
+| Correspondent | Add, edit, delete or view Correspondents.                                                                                                                                |
+| CustomField   | Add, edit, delete or view Custom Fields.                                                                                                                                 |
+| Document      | Add, edit, delete or view Documents.                                                                                                                                     |
+| DocumentType  | Add, edit, delete or view Document Types.                                                                                                                                |
+| Group         | Add, edit, delete or view Groups.                                                                                                                                        |
+| MailAccount   | Add, edit, delete or view Mail Accounts.                                                                                                                                 |
+| MailRule      | Add, edit, delete or view Mail Rules.                                                                                                                                    |
+| Note          | Add, edit, delete or view Notes.                                                                                                                                         |
+| PaperlessTask | View or dismiss (_Change_) File Tasks.                                                                                                                                   |
+| SavedView     | Add, edit, delete or view Saved Views.                                                                                                                                   |
+| ShareLink     | Add, delete or view Share Links.                                                                                                                                         |
+| StoragePath   | Add, edit, delete or view Storage Paths.                                                                                                                                 |
+| Tag           | Add, edit, delete or view Tags.                                                                                                                                          |
+| UISettings    | Add, edit, delete or view the UI settings that are used by the web app.<br/>:warning: **Users that will access the web UI must be granted at least _View_ permissions.** |
+| User          | Add, edit, delete or view Users.                                                                                                                                         |
+| Workflow      | Add, edit, delete or view Workflows.<br/>Note that Workflows are global, in other words all users who can access workflows have access to the same set of them.          |
+
+#### Detailed Explanation of Object Permissions {#object-permissions}
+
+| Type  | Details                                                                                                                                                                                                                                                                                                                                  |
+| ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Owner | By default objects are only visible and editable by their owner.<br/>Only the object owner can grant permissions to other users or groups.<br/>Additionally, only document owners can create share links and add / remove custom fields.<br/>For backwards compatibility objects can have no owner which makes them visible to any user. |
+| View  | Confers the ability to view (not edit) a document, tag, etc.<br/>Users without 'view' (or higher) permissions will be shown _'Private'_ in place of the object name for example when viewing a document with a tag for which the user doesn't have permissions.                                                                          |
+| Edit  | Confers the ability to edit (and view) a document, tag, etc.                                                                                                                                                                                                                                                                             |
+
+### Password reset
+
+In order to enable the password reset feature you will need to setup an SMTP backend, see
+[`PAPERLESS_EMAIL_HOST`](configuration.md#PAPERLESS_EMAIL_HOST). If your installation does not have
+[`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) set, the reset link included in emails will use the server host.
+
+## Workflows
+
+!!! note
+
+    v2.3 added "Workflows" and existing "Consumption Templates" were converted automatically to the new more powerful format.
+
+Workflows allow hooking into the Paperless-ngx document pipeline, for example to alter what metadata (tags, doc types) and
+permissions (owner, privileges) are assigned to documents. Workflows can have multiple 'triggers' and 'actions'. Triggers
+are events (with optional filtering rules) that will cause the workflow to be run and actions are the set of sequential
+actions to apply.
+
+In general, workflows and any actions they contain are applied sequentially by sort order. For "assignment" actions, subsequent
+workflow actions will override previous assignments, except for assignments that accept multiple items e.g. tags, custom
+fields and permissions, which will be merged.
+
+### Workflow Triggers
+
+Currently, there are three events that correspond to workflow trigger 'types':
+
+1. **Consumption Started**: _before_ a document is consumed, so events can include filters by source (mail, consumption
+   folder or API), file path, file name, mail rule
+2. **Document Added**: _after_ a document is added. At this time, file path and source information is no longer available,
+   but the document content has been extracted and metadata such as document type, tags, etc. have been set, so these can now
+   be used for filtering.
+3. **Document Updated**: when a document is updated. Similar to 'added' events, triggers can include filtering by content matching,
+   tags, doc type, or correspondent.
+
+The following flow diagram illustrates the three trigger types:
+
+```mermaid
+flowchart TD
+    consumption{"Matching
+    'Consumption'
+    trigger(s)"}
+
+    added{"Matching
+    'Added'
+    trigger(s)"}
+
+    updated{"Matching
+    'Updated'
+    trigger(s)"}
+
+    A[New Document] --> consumption
+    consumption --> |Yes| C[Workflow Actions Run]
+    consumption --> |No| D
+    C --> D[Document Added]
+    D -- Paperless-ngx 'matching' of tags, etc. --> added
+    added --> |Yes| F[Workflow Actions Run]
+    added --> |No| G
+    F --> G[Document Finalized]
+    H[Existing Document Changed] --> updated
+    updated --> |Yes| J[Workflow Actions Run]
+    updated --> |No| K
+    J --> K[Document Saved]
+```
+
+#### Filters {#workflow-trigger-filters}
+
+Workflows allow you to filter by:
+
+-   Source, e.g. documents uploaded via consume folder, API (& the web UI) and mail fetch
+-   File name, including wildcards e.g. \*.pdf will apply to all pdfs
+-   File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
+    example, automatically assigning documents to different owners based on the upload directory.
+-   Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
+-   Content matching (`Added` and `Updated` triggers only). Filter document content using the matching settings.
+-   Tags (`Added` and `Updated` triggers only). Filter for documents with any of the specified tags
+-   Document type (`Added` and `Updated` triggers only). Filter documents with this doc type
+-   Correspondent (`Added` and `Updated` triggers only). Filter documents with this correspondent
+
+### Workflow Actions
+
+There are currently two types of workflow actions, "Assignment", which can assign:
+
+-   Title, see [title placeholders](usage.md#title-placeholders) below
+-   Tags, correspondent, document type and storage path
+-   Document owner
+-   View and / or edit permissions to users or groups
+-   Custom fields. Note that no value for the field will be set
+
+and "Removal" actions, which can remove either all of or specific sets of the following:
+
+-   Tags, correspondents, document types or storage paths
+-   Document owner
+-   View and / or edit permissions
+-   Custom fields
+
+#### Title placeholders
+
+Workflow titles can include placeholders but the available options differ depending on the type of
+workflow trigger. This is because at the time of consumption (when the title is to be set), no automatic tags etc. have been
+applied. You can use the following placeholders with any trigger type:
+
+-   `{correspondent}`: assigned correspondent name
+-   `{document_type}`: assigned document type name
+-   `{owner_username}`: assigned owner username
+-   `{added}`: added datetime
+-   `{added_year}`: added year
+-   `{added_year_short}`: added year
+-   `{added_month}`: added month
+-   `{added_month_name}`: added month name
+-   `{added_month_name_short}`: added month short name
+-   `{added_day}`: added day
+-   `{added_time}`: added time in HH:MM format
+-   `{original_filename}`: original file name without extension
+
+The following placeholders are only available for "added" or "updated" triggers
+
+-   `{created}`: created datetime
+-   `{created_year}`: created year
+-   `{created_year_short}`: created year
+-   `{created_month}`: created month
+-   `{created_month_name}`: created month name
+-   `{created_month_name_short}`: created month short name
+-   `{created_day}`: created day
+-   `{created_time}`: created time in HH:MM format
+
+### Workflow permissions
+
+All users who have application permissions for editing workflows can see the same set
+of workflows. In other words, workflows themselves intentionally do not have an owner or permissions.
+
+Given their potentially far-reaching capabilities, you may want to restrict access to workflows.
+
+Upon migration, existing installs will grant access to workflows to users who can add
+documents (and superusers who can always access all parts of the app).
+
+## Custom Fields {#custom-fields}
+
+Paperless-ngx supports the use of custom fields for documents as of v2.0, allowing a user
+to optionally attach data to documents which does not fit in the existing set of fields
+Paperless-ngx provides.
+
+1. First, create a custom field (under "Manage"), with a given name and data type. This could be something like "Invoice Number" or "Date Paid", with a data type of "Number", "Date", "String", etc.
+2. Once created, a field can be used with documents and data stored. To do so, use the "Custom Fields" menu on the document detail page, choose your existing field from the dropdown. Once the field is visible in the form you can enter the appropriate data which will be validated according to the custom field "data type".
+3. Fields can be removed by hovering over the field name revealing a "Remove" button.
+
+!!! important
+
+    Added / removed fields, as well as any data, is not saved to the document until you
+    actually hit the "Save" button, similar to other changes on the document details page.
+
+!!! note
+
+    Once the data type for a field is set, it cannot be changed.
+
+Multiple fields may be attached to a document but the same field name cannot be assigned multiple times to the a single document.
+
+The following custom field types are supported:
+
+-   `Text`: any text
+-   `Boolean`: true / false (check / unchecked) field
+-   `Date`: date
+-   `URL`: a valid url
+-   `Integer`: integer number e.g. 12
+-   `Number`: float number e.g. 12.3456
+-   `Monetary`: [ISO 4217 currency code](https://en.wikipedia.org/wiki/ISO_4217#List_of_ISO_4217_currency_codes) and a number with exactly two decimals, e.g. USD12.30
+-   `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
+-   `Select`: a pre-defined list of strings from which the user can choose
+
+## Share Links
+
+Paperless-ngx added the ability to create shareable links to files in version 2.0. You can find the button for this on the document detail screen.
+
+-   Share links do not require a user to login and thus link directly to a file.
+-   Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
+-   Links can optionally have an expiration time set.
+-   After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
+
+!!! tip
+
+    If your paperless-ngx instance is behind a reverse-proxy you may want to create an exception to bypass any authentication layers that are part of your setup in order to make links truly publicly-accessible. Of course, do so with caution.
+
+## PDF Actions
+
+Paperless-ngx supports four basic editing operations for PDFs (these operations currently cannot be performed on non-PDF files):
+
+-   Merging documents: available when selecting multiple documents for 'bulk editing'.
+-   Rotating documents: available when selecting multiple documents for 'bulk editing' and from an individual document's details page.
+-   Splitting documents: available from an individual document's details page.
+-   Deleting pages: available from an individual document's details page.
+
+!!! important
+
+    Note that rotation and deleting pages alter the Paperless-ngx _original_ file, which would, for example, invalidate a digital signature.
+
+## Document History
+
+As of version 2.7, Paperless-ngx automatically records all changes to a document and records this in an audit log. The feature requires [`PAPERLESS_AUDIT_LOG_ENABLED`](configuration.md#PAPERLESS_AUDIT_LOG_ENABLED) be enabled, which it is by default as of version 2.7.
+Changes to documents are visible under the "History" tab. Note that certain changes such as those made by workflows, record the 'actor'
+as "System".
+
+## Document Trash
+
+When you first delete a document it is moved to the 'trash' until either it is explicitly deleted or it is automatically removed after a set amount of time has passed.
+You can set how long documents remain in the trash before being automatically deleted with [`PAPERLESS_EMPTY_TRASH_DELAY`](configuration.md#PAPERLESS_EMPTY_TRASH_DELAY), which defaults
+to 30 days. Until the file is actually deleted (e.g. the trash is emptied), all files and database content remains intact and can be restored at any point up until that time.
+
+Additionally you may configure a directory where deleted files are moved to when they the trash is emptied with [`PAPERLESS_EMPTY_TRASH_DIR`](configuration.md#PAPERLESS_EMPTY_TRASH_DIR).
+Note that the empty trash directory only stores the original file, the archive file and all database information is permanently removed once a document is fully deleted.
+
 ## Best practices {#basic-searching}
 
 Paperless offers a couple tools that help you organize your document
@@ -307,21 +558,31 @@ the system.
 Here are a couple examples of tags and types that you could use in your
 collection.
 
-- An `inbox` tag for newly added documents that you haven't manually
-  edited yet.
-- A tag `car` for everything car related (repairs, registration,
-  insurance, etc)
-- A tag `todo` for documents that you still need to do something with,
-  such as reply, or perform some task online.
-- A tag `bank account x` for all bank statement related to that
-  account.
-- A tag `mail` for anything that you added to paperless via its mail
-  processing capabilities.
-- A tag `missing_metadata` when you still need to add some metadata to
-  a document, but can't or don't want to do this right now.
+-   An `inbox` tag for newly added documents that you haven't manually
+    edited yet.
+-   A tag `car` for everything car related (repairs, registration,
+    insurance, etc)
+-   A tag `todo` for documents that you still need to do something with,
+    such as reply, or perform some task online.
+-   A tag `bank account x` for all bank statement related to that
+    account.
+-   A tag `mail` for anything that you added to paperless via its mail
+    processing capabilities.
+-   A tag `missing_metadata` when you still need to add some metadata to
+    a document, but can't or don't want to do this right now.
 
 ## Searching {#basic-usage_searching}
 
+### Global search
+
+The top search bar in the web UI performs a "global" search of the various
+objects Paperless-ngx uses, including documents, tags, workflows, etc. Only
+objects for which the user has appropriate permissions are returned. For
+documents, if there are < 3 results, "advanced" search results (which use
+the document index) will also be included. This can be disabled under settings.
+
+### Document searches
+
 Paperless offers an extensive searching mechanism that is designed to
 allow you to quickly find a document you're looking for (for example,
 that thing that just broke and you bought a couple months ago, that
@@ -377,6 +638,12 @@ language](https://whoosh.readthedocs.io/en/latest/querylang.html). For
 details on what date parsing utilities are available, see [Date
 parsing](https://whoosh.readthedocs.io/en/latest/dates.html#parsing-date-queries).
 
+## Keyboard shortcuts / hotkeys
+
+A list of available hotkeys can be shown on any page using <kbd>Shift</kbd> +
+<kbd>?</kbd>. The help dialog shows only the keys that are currently available
+based on which area of Paperless-ngx you are using.
+
 ## The recommended workflow {#usage-recommended-workflow}
 
 Once you have familiarized yourself with paperless and are ready to use
@@ -391,8 +658,8 @@ The following diagram shows how easy it is to manage your documents.
 
 ### Preparations in paperless
 
-- Create an inbox tag that gets assigned to all new documents.
-- Create a TODO tag.
+-   Create an inbox tag that gets assigned to all new documents.
+-   Create a TODO tag.
 
 ### Processing of the physical documents
 
@@ -458,7 +725,7 @@ Once you have scanned in a document, proceed in paperless as follows.
     paperless will assign them automatically. After consuming a couple
     documents, you can even ask paperless to *learn* when to assign tags and
     correspondents by itself. For details on this feature, see
-    [advanced matching](/advanced_usage#matching).
+    [advanced matching](advanced_usage.md#matching).
 
 ### Task management
 
@@ -466,78 +733,78 @@ Some documents require attention and require you to act on the document.
 You may take two different approaches to handle these documents based on
 how regularly you intend to scan documents and use paperless.
 
-- If you scan and process your documents in paperless regularly,
-  assign a TODO tag to all scanned documents that you need to process.
-  Create a saved view on the dashboard that shows all documents with
-  this tag.
-- If you do not scan documents regularly and use paperless solely for
-  archiving, create a physical todo box next to your physical inbox
-  and put documents you need to process in the TODO box. When you
-  performed the task associated with the document, move it to the
-  inbox.
+-   If you scan and process your documents in paperless regularly,
+    assign a TODO tag to all scanned documents that you need to process.
+    Create a saved view on the dashboard that shows all documents with
+    this tag.
+-   If you do not scan documents regularly and use paperless solely for
+    archiving, create a physical todo box next to your physical inbox
+    and put documents you need to process in the TODO box. When you
+    performed the task associated with the document, move it to the
+    inbox.
 
 ## Architecture
 
 Paperless-ngx consists of the following components:
 
-- **The webserver:** This serves the administration pages, the API,
-  and the new frontend. This is the main tool you'll be using to interact
-  with paperless. You may start the webserver directly with
+-   **The webserver:** This serves the administration pages, the API,
+    and the new frontend. This is the main tool you'll be using to interact
+    with paperless. You may start the webserver directly with
 
-  ```shell-session
-  $ cd /path/to/paperless/src/
-  $ gunicorn -c ../gunicorn.conf.py paperless.wsgi
-  ```
+    ```shell-session
+    $ cd /path/to/paperless/src/
+    $ gunicorn -c ../gunicorn.conf.py paperless.wsgi
+    ```
 
-  or by any other means such as Apache `mod_wsgi`.
+    or by any other means such as Apache `mod_wsgi`.
 
-- **The consumer:** This is what watches your consumption folder for
-  documents. However, the consumer itself does not really consume your
-  documents. Now it notifies a task processor that a new file is ready
-  for consumption. I suppose it should be named differently. This was
-  also used to check your emails, but that's now done elsewhere as
-  well.
+-   **The consumer:** This is what watches your consumption folder for
+    documents. However, the consumer itself does not really consume your
+    documents. Now it notifies a task processor that a new file is ready
+    for consumption. I suppose it should be named differently. This was
+    also used to check your emails, but that's now done elsewhere as
+    well.
 
-  Start the consumer with the management command `document_consumer`:
+    Start the consumer with the management command `document_consumer`:
 
-  ```shell-session
-  $ cd /path/to/paperless/src/
-  $ python3 manage.py document_consumer
-  ```
+    ```shell-session
+    $ cd /path/to/paperless/src/
+    $ python3 manage.py document_consumer
+    ```
 
-- **The task processor:** Paperless relies on [Celery - Distributed
-  Task Queue](https://docs.celeryq.dev/en/stable/index.html) for doing
-  most of the heavy lifting. This is a task queue that accepts tasks
-  from multiple sources and processes these in parallel. It also comes
-  with a scheduler that executes certain commands periodically.
+-   **The task processor:** Paperless relies on [Celery - Distributed
+    Task Queue](https://docs.celeryq.dev/en/stable/index.html) for doing
+    most of the heavy lifting. This is a task queue that accepts tasks
+    from multiple sources and processes these in parallel. It also comes
+    with a scheduler that executes certain commands periodically.
 
-  This task processor is responsible for:
+    This task processor is responsible for:
 
-  - Consuming documents. When the consumer finds new documents, it
-    notifies the task processor to start a consumption task.
-  - The task processor also performs the consumption of any
-    documents you upload through the web interface.
-  - Consuming emails. It periodically checks your configured
-    accounts for new emails and notifies the task processor to
-    consume the attachment of an email.
-  - Maintaining the search index and the automatic matching
-    algorithm. These are things that paperless needs to do from time
-    to time in order to operate properly.
+    -   Consuming documents. When the consumer finds new documents, it
+        notifies the task processor to start a consumption task.
+    -   The task processor also performs the consumption of any
+        documents you upload through the web interface.
+    -   Consuming emails. It periodically checks your configured
+        accounts for new emails and notifies the task processor to
+        consume the attachment of an email.
+    -   Maintaining the search index and the automatic matching
+        algorithm. These are things that paperless needs to do from time
+        to time in order to operate properly.
 
-  This allows paperless to process multiple documents from your
-  consumption folder in parallel! On a modern multi core system, this
-  makes the consumption process with full OCR blazingly fast.
+    This allows paperless to process multiple documents from your
+    consumption folder in parallel! On a modern multi core system, this
+    makes the consumption process with full OCR blazingly fast.
 
-  The task processor comes with a built-in admin interface that you
-  can use to check whenever any of the tasks fail and inspect the
-  errors (i.e., wrong email credentials, errors during consuming a
-  specific file, etc).
+    The task processor comes with a built-in admin interface that you
+    can use to check whenever any of the tasks fail and inspect the
+    errors (i.e., wrong email credentials, errors during consuming a
+    specific file, etc).
 
-- A [redis](https://redis.io/) message broker: This is a really
-  lightweight service that is responsible for getting the tasks from
-  the webserver and the consumer to the task scheduler. These run in a
-  different process (maybe even on different machines!), and
-  therefore, this is necessary.
+-   A [redis](https://redis.io/) message broker: This is a really
+    lightweight service that is responsible for getting the tasks from
+    the webserver and the consumer to the task scheduler. These run in a
+    different process (maybe even on different machines!), and
+    therefore, this is necessary.
 
-- Optional: A database server. Paperless supports PostgreSQL, MariaDB
-  and SQLite for storing its data.
+-   Optional: A database server. Paperless supports PostgreSQL, MariaDB
+    and SQLite for storing its data.

gunicorn.conf.py

@@ -37,11 +37,11 @@ def worker_int(worker):
     id2name = {th.ident: th.name for th in threading.enumerate()}
     code = []
     for threadId, stack in sys._current_frames().items():
-        code.append("\n# Thread: %s(%d)" % (id2name.get(threadId, ""), threadId))
+        code.append(f"\n# Thread: {id2name.get(threadId, '')}({threadId})")
         for filename, lineno, name, line in traceback.extract_stack(stack):
-            code.append('File: "%s", line %d, in %s' % (filename, lineno, name))
+            code.append(f'File: "{filename}", line {lineno}, in {name}')
             if line:
-                code.append("  %s" % (line.strip()))
+                code.append(f"  {line.strip()}")
     worker.log.debug("\n".join(code))
 
 

install-paperless-ngx.sh

@@ -38,7 +38,6 @@ ask_docker_folder() {
 			echo "Invalid folder: $result"
 		fi
 
-
 	done
 }
 
@@ -57,14 +56,9 @@ if ! command -v docker &> /dev/null ; then
 	exit 1
 fi
 
-DOCKER_COMPOSE_CMD="docker-compose"
-if ! command -v ${DOCKER_COMPOSE_CMD} ; then
-	if docker compose version &> /dev/null ; then
-		DOCKER_COMPOSE_CMD="docker compose"
-	else
-		echo "docker-compose executable not found. Is docker-compose installed?"
-		exit 1
-	fi
+if ! docker compose &> /dev/null ; then
+	echo "docker compose plugin not found. Is docker compose installed?"
+	exit 1
 fi
 
 # Check if user has permissions to run Docker by trying to get the status of Docker (docker status).
@@ -72,12 +66,22 @@ fi
 if ! docker stats --no-stream &> /dev/null ; then
 	echo ""
 	echo "WARN: It look like the current user does not have Docker permissions."
-	echo "WARN: Use 'sudo usermod -aG docker $USER' to assign Docker permissions to the user."
+	echo "WARN: Use 'sudo usermod -aG docker $USER' to assign Docker permissions to the user (may require restarting shell)."
 	echo ""
 	sleep 3
 fi
 
-default_time_zone=$(timedatectl show -p Timezone --value)
+# Added handling for timezone for busybox based linux, not having timedatectl available (i.e. QNAP QTS)
+# if neither timedatectl nor /etc/TZ is succeeding, defaulting to GMT.
+if  command -v timedatectl &> /dev/null ; then
+	default_time_zone=$(timedatectl show -p Timezone --value)
+elif [ -f /etc/TZ ] && [ -f /etc/tzlist ] ; then
+	TZ=$(cat /etc/TZ)
+	default_time_zone=$(grep -B 1 -m 1 "$TZ" /etc/tzlist | head -1 | cut -f 2 -d =)
+else
+	echo "WARN: unable to detect timezone, defaulting to Etc/UTC"
+	default_time_zone="Etc/UTC"
+fi
 
 set -e
 
@@ -321,7 +325,8 @@ fi
 wget "https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docker/compose/docker-compose.$DOCKER_COMPOSE_VERSION.yml" -O docker-compose.yml
 wget "https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docker/compose/.env" -O .env
 
-SECRET_KEY=$(tr --delete --complement 'a-zA-Z0-9' < /dev/urandom 2>/dev/null | head --bytes 64)
+SECRET_KEY=$(LC_ALL=C tr -dc 'a-zA-Z0-9!#$%&()*+,-./:;<=>?@[\]^_`{|}~' < /dev/urandom | dd bs=1 count=64 2>/dev/null)
+
 
 DEFAULT_LANGUAGES=("deu eng fra ita spa")
 
@@ -340,7 +345,7 @@ read -r -a OCR_LANGUAGES_ARRAY <<< "${_split_langs}"
 	fi
 	echo "PAPERLESS_TIME_ZONE=$TIME_ZONE"
 	echo "PAPERLESS_OCR_LANGUAGE=$OCR_LANGUAGE"
-	echo "PAPERLESS_SECRET_KEY=$SECRET_KEY"
+	echo "PAPERLESS_SECRET_KEY='$SECRET_KEY'"
 	if [[ ! ${DEFAULT_LANGUAGES[*]} =~ ${OCR_LANGUAGES_ARRAY[*]} ]] ; then
 		echo "PAPERLESS_OCR_LANGUAGES=${OCR_LANGUAGES_ARRAY[*]}"
 	fi
@@ -382,8 +387,16 @@ if [ "$l1" -eq "$l2" ] ; then
 fi
 
 
-${DOCKER_COMPOSE_CMD} pull
+docker compose pull
 
-${DOCKER_COMPOSE_CMD} run --rm -e DJANGO_SUPERUSER_PASSWORD="$PASSWORD" webserver createsuperuser --noinput --username "$USERNAME" --email "$EMAIL"
+if [ "$DATABASE_BACKEND" == "postgres" ] || [ "$DATABASE_BACKEND" == "mariadb" ] ; then
+	echo "Starting DB first for initialization"
+	docker compose up --detach db
+	# hopefully enough time for even the slower systems
+	sleep 15
+	docker compose stop
+fi
 
-${DOCKER_COMPOSE_CMD} up --detach
+docker compose run --rm -e DJANGO_SUPERUSER_PASSWORD="$PASSWORD" webserver createsuperuser --noinput --username "$USERNAME" --email "$EMAIL"
+
+docker compose up --detach

mkdocs.yml

@@ -6,6 +6,12 @@ theme:
     text: Roboto
     code: Roboto Mono
   palette:
+    # Palette toggle for automatic mode
+    - media: "(prefers-color-scheme)"
+      toggle:
+        icon: material/brightness-auto
+        name: Switch to light mode
+
     # Palette toggle for light mode
     - media: "(prefers-color-scheme: light)"
       scheme: default
@@ -18,7 +24,7 @@ theme:
       scheme: slate
       toggle:
         icon: material/brightness-4
-        name: Switch to light mode
+        name: Switch to system preference
   features:
     - navigation.tabs
     - navigation.top
@@ -28,6 +34,7 @@ theme:
     repo: fontawesome/brands/github
   favicon: assets/favicon.png
 repo_url: https://github.com/paperless-ngx/paperless-ngx
+repo_name: paperless-ngx/paperless-ngx
 edit_uri: blob/main/docs/
 extra_css:
   - assets/extra.css
@@ -42,6 +49,15 @@ markdown_extensions:
   - pymdownx.superfences
   - pymdownx.inlinehilite
   - pymdownx.snippets
+  - footnotes
+  - pymdownx.superfences:
+      custom_fences:
+        - name: mermaid
+          class: mermaid
+          format: !!python/name:pymdownx.superfences.fence_code_format
+  - pymdownx.emoji:
+      emoji_index: !!python/name:material.extensions.emoji.twemoji
+      emoji_generator: !!python/name:material.extensions.emoji.to_svg
 strict: true
 nav:
     - index.md
@@ -64,3 +80,8 @@ extra:
       link: https://hub.docker.com/r/paperlessngx/paperless-ngx
     - icon: material/chat
       link: https://matrix.to/#/#paperless:matrix.org
+plugins:
+  - search
+  - glightbox:
+       skip_classes:
+         - no-lightbox

paperless-ngx.code-workspace

@@ -0,0 +1,41 @@
+{
+	"folders": [
+		{
+			"path": "."
+		},
+		{
+			"path": "./src",
+			"name": "Backend"
+		},
+		{
+			"path": "./src-ui",
+			"name": "Frontend"
+		},
+		{
+			"path": "./.github",
+			"name": "CI/CD"
+		},
+		{
+			"path": "./docs",
+			"name": "Documentation"
+		}
+
+	],
+	"settings": {
+		"files.exclude": {
+			"**/__pycache__": true,
+			"**/.mypy_cache": true,
+			"**/.ruff_cache": true,
+			"**/.pytest_cache": true,
+			"**/.idea": true,
+			"**/.venv": true,
+			"**/.coverage": true,
+			"**/coverage.json": true
+		},
+		"python.defaultInterpreterPath": ".venv/bin/python3",
+	},
+	"extensions": {
+		"recommendations": ["ms-python.python", "charliermarsh.ruff", "editorconfig.editorconfig"],
+		"unwantedRecommendations": ["ms-python.black-formatter"]
+	}
+}

paperless.conf.example

@@ -19,7 +19,7 @@
 
 #PAPERLESS_CONSUMPTION_DIR=../consume
 #PAPERLESS_DATA_DIR=../data
-#PAPERLESS_TRASH_DIR=
+#PAPERLESS_EMPTY_TRASH_DIR=
 #PAPERLESS_MEDIA_ROOT=../media
 #PAPERLESS_STATICDIR=../static
 #PAPERLESS_FILENAME_FORMAT=
@@ -66,6 +66,13 @@
 #PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=false
 #PAPERLESS_CONSUMER_ENABLE_BARCODES=false
 #PAPERLESS_CONSUMER_BARCODE_STRING=PATCHT
+#PAPERLESS_CONSUMER_BARCODE_UPSCALE=0.0
+#PAPERLESS_CONSUMER_BARCODE_DPI=300
+#PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE=false
+#PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING={"TAG:(.*)": "\\g<1>"}
+#PAPERLESS_CONSUMER_ENABLE_COLLATE_DOUBLE_SIDED=false
+#PAPERLESS_CONSUMER_COLLATE_DOUBLE_SIDED_SUBDIR_NAME=double-sided
+#PAPERLESS_CONSUMER_COLLATE_DOUBLE_SIDED_TIFF_SUPPORT=false
 #PAPERLESS_PRE_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_POST_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_FILENAME_DATE_ORDER=YMD

scripts/post-consumption-example.sh

@@ -14,6 +14,7 @@ following additional information about it:
 * Thumbnail Path: ${DOCUMENT_THUMBNAIL_PATH}
 * Download URL: ${DOCUMENT_DOWNLOAD_URL}
 * Thumbnail URL: ${DOCUMENT_THUMBNAIL_URL}
+* Owner Name: ${DOCUMENT_OWNER}
 * Correspondent: ${DOCUMENT_CORRESPONDENT}
 * Tags: ${DOCUMENT_TAGS}
 

scripts/start_services.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
+docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:15
 docker run -d -p 6379:6379 redis:latest
 docker run -p 3000:3000 -d gotenberg/gotenberg:7.8 gotenberg --chromium-disable-javascript=true --chromium-allow-list="file:///tmp/.*"
-docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest
+docker run -p 9998:9998 -d docker.io/apache/tika:latest

src-ui/.eslintrc.json

@@ -1,7 +1,8 @@
 {
   "root": true,
   "ignorePatterns": [
-    "projects/**/*"
+    "projects/**/*",
+    "/src/app/components/common/pdf-viewer/**"
   ],
   "overrides": [
     {
@@ -24,7 +25,7 @@
           "error",
           {
             "type": "attribute",
-            "prefix": "app",
+            "prefix": "pngx",
             "style": "camelCase"
           }
         ],
@@ -32,7 +33,7 @@
           "error",
           {
             "type": "element",
-            "prefix": "app",
+            "prefix": "pngx",
             "style": "kebab-case"
           }
         ]

src-ui/angular.json

@@ -12,39 +12,51 @@
       },
       "root": "",
       "sourceRoot": "src",
-      "prefix": "app",
+      "prefix": "pngx",
       "i18n": {
         "sourceLocale": "en-US",
         "locales": {
           "ar-AR": "src/locale/messages.ar_AR.xlf",
+          "af-ZA": "src/locale/messages.af_ZA.xlf",
+          "bg-BG": "src/locale/messages.bg_BG.xlf",
           "be-BY": "src/locale/messages.be_BY.xlf",
           "ca-ES": "src/locale/messages.ca_ES.xlf",
           "cs-CZ": "src/locale/messages.cs_CZ.xlf",
           "da-DK": "src/locale/messages.da_DK.xlf",
           "de-DE": "src/locale/messages.de_DE.xlf",
+          "el-GR": "src/locale/messages.el_GR.xlf",
           "en-GB": "src/locale/messages.en_GB.xlf",
           "es-ES": "src/locale/messages.es_ES.xlf",
           "fi-FI": "src/locale/messages.fi_FI.xlf",
           "fr-FR": "src/locale/messages.fr_FR.xlf",
+          "hu-HU": "src/locale/messages.hu_HU.xlf",
           "it-IT": "src/locale/messages.it_IT.xlf",
+          "ja-JP": "src/locale/messages.ja_JP.xlf",
           "lb-LU": "src/locale/messages.lb_LU.xlf",
+          "ko-KR": "src/locale/messages.ko_KR.xlf",
           "nl-NL": "src/locale/messages.nl_NL.xlf",
+          "no-NO": "src/locale/messages.no_NO.xlf",
           "pl-PL": "src/locale/messages.pl_PL.xlf",
           "pt-BR": "src/locale/messages.pt_BR.xlf",
           "pt-PT": "src/locale/messages.pt_PT.xlf",
           "ro-RO": "src/locale/messages.ro_RO.xlf",
           "ru-RU": "src/locale/messages.ru_RU.xlf",
+          "sk-SK": "src/locale/messages.sk_SK.xlf",
           "sl-SI": "src/locale/messages.sl_SI.xlf",
           "sr-CS": "src/locale/messages.sr_CS.xlf",
           "sv-SE": "src/locale/messages.sv_SE.xlf",
           "tr-TR": "src/locale/messages.tr_TR.xlf",
+          "uk-UA": "src/locale/messages.uk_UA.xlf",
           "zh-CN": "src/locale/messages.zh_CN.xlf"
         }
       },
       "architect": {
         "build": {
-          "builder": "@angular-devkit/build-angular:browser",
+          "builder": "@angular-builders/custom-webpack:browser",
           "options": {
+            "customWebpackConfig": {
+                "path": "./extra-webpack.config.ts"
+            },
             "outputPath": "dist/paperless-ui",
             "outputHashing": "none",
             "index": "src/index.html",
@@ -58,8 +70,8 @@
               "src/assets",
               "src/manifest.webmanifest",
               {
-                "glob": "pdf.worker.min.js",
-                "input": "node_modules/pdfjs-dist/build/",
+                "glob": "{pdf.worker.min.mjs,pdf.min.mjs}",
+                "input": "node_modules/pdfjs-dist/legacy/build/",
                 "output": "/assets/js/"
               }
             ],
@@ -68,7 +80,8 @@
             ],
             "scripts": [],
             "allowedCommonJsDependencies": [
-              "ng2-pdf-viewer"
+              "ng2-pdf-viewer",
+              "file-saver"
             ],
             "vendorChunk": true,
             "extractLicenses": false,
@@ -102,7 +115,7 @@
                 {
                   "type": "anyComponentStyle",
                   "maximumWarning": "6kb",
-                  "maximumError": "10kb"
+                  "maximumError": "30kb"
                 }
               ]
             },
@@ -115,20 +128,20 @@
           "defaultConfiguration": ""
         },
         "serve": {
-          "builder": "@angular-devkit/build-angular:dev-server",
+          "builder": "@angular-builders/custom-webpack:dev-server",
           "options": {
-            "browserTarget": "paperless-ui:build:en-US"
+            "buildTarget": "paperless-ui:build:en-US"
           },
           "configurations": {
             "production": {
-              "browserTarget": "paperless-ui:build:production"
+              "buildTarget": "paperless-ui:build:production"
             }
           }
         },
         "extract-i18n": {
-          "builder": "@angular-devkit/build-angular:extract-i18n",
+          "builder": "@angular-builders/custom-webpack:extract-i18n",
           "options": {
-            "browserTarget": "paperless-ui:build"
+            "buildTarget": "paperless-ui:build"
           }
         },
         "test": {
@@ -159,7 +172,6 @@
       }
     }
   },
-  "defaultProject": "paperless-ui",
   "cli": {
     "schematicCollections": [
       "@angular-eslint/schematics"